Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4244 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.9838. Min Act: -0.1700
Data Index: 3390441 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.7338. Min Act: -0.1700
Data Index: 6207694 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.6088. Min Act: -0.1700
Data Index: 1682366 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.6088. Min Act: -0.1700
Data Index: 2232954 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.5463. Min Act: -0.1700
Data Index: 7670694 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.4838. Min Act: -0.1700
Data Index: 6327351 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.4213. Min Act: -0.1700
Data Index: 5981061 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.4213. Min Act: -0.1700
Data Index: 1469382 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.3588. Min Act: -0.1700
Data Index: 4931011 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.3588. Min Act: -0.1700
Data Index: 1956201 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2963. Min Act: -0.1700
Data Index: 8075995 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2963. Min Act: -0.1700
Data Index: 1605284 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2963. Min Act: -0.1700
Data Index: 4948035 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2963. Min Act: -0.1700
Data Index: 3506708 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2963. Min Act: -0.1700
Data Index: 2716559 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2338. Min Act: -0.1700
Data Index: 7086968 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2338. Min Act: -0.1700
Data Index: 1377529 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2963. Min Act: -0.1700
Data Index: 2584420 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.2338. Min Act: -0.1700
Data Index: 2804192 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9838. Min Range: -10.9838
Max Act: 10.1713. Min Act: -0.1700
Data Index: 420299 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19