Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5390 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.7381. Min Act: -0.1700
Data Index: 2062288 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.7069. Min Act: -0.1700
Data Index: 6224029 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6131. Min Act: -0.1700
Data Index: 3543009 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6131. Min Act: -0.1700
Data Index: 1433567 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5819. Min Act: -0.1700
Data Index: 7655380 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5819. Min Act: -0.1700
Data Index: 480521 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.6131. Min Act: -0.1700
Data Index: 3857841 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5819. Min Act: -0.1700
Data Index: 7894845 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5819. Min Act: -0.1700
Data Index: 5294572 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 139140 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 6729979 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 8741482 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 4979552 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 3017779 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 4686714 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5506. Min Act: -0.1700
Data Index: 2154182 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5194. Min Act: -0.1700
Data Index: 2559372 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5194. Min Act: -0.1700
Data Index: 7488623 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5194. Min Act: -0.1700
Data Index: 1937853 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7381. Min Range: -4.7381
Max Act: 4.5194. Min Act: -0.1700
Data Index: 7655379 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19