Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3276. Min Range: -4.3276
Max Act: 4.3276. Min Act: -0.1700
Data Index: 390094 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3276. Min Range: -4.3276
Max Act: 4.1713. Min Act: -0.1700
Data Index: 5442799 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3276. Min Range: -4.3276
Max Act: 4.1401. Min Act: -0.1700
Data Index: 4213967 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3276. Min Range: -4.3276
Max Act: 4.1088. Min Act: -0.1700
Data Index: 3112890 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3276. Min Range: -4.3276
Max Act: 4.1088. Min Act: -0.1700
Data Index: 3392862 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3276. Min Range: -4.3276
Max Act: 4.0151. Min Act: -0.1700
Data Index: 6160914 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3276. Min Range: -4.3276
Max Act: 4.0151. Min Act: -0.1700
Data Index: 3008798 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3276. Min Range: -4.3276
Max Act: 4.0151. Min Act: -0.1700
Data Index: 6070502 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9838. Min Act: -0.1700
Data Index: 6599465 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9838. Min Act: -0.1700
Data Index: 1262653 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9838. Min Act: -0.1700
Data Index: 3154635 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9525. Min Act: -0.1700
Data Index: 5677012 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9525. Min Act: -0.1700
Data Index: 951918 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9525. Min Act: -0.1700
Data Index: 116516 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9213. Min Act: -0.1700
Data Index: 1462344 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9213. Min Act: -0.1700
Data Index: 4356763 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9213. Min Act: -0.1700
Data Index: 8108671 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9213. Min Act: -0.1700
Data Index: 8012173 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.9213. Min Act: -0.1700
Data Index: 1779659 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3276. Min Range: -4.3276
Max Act: 3.8900. Min Act: -0.1700
Data Index: 2477035 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19