Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0333. Min Range: -4.0333
Max Act: 4.0333. Min Act: -0.1700
Data Index: 8290850 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0333. Min Range: -4.0333
Max Act: 4.0021. Min Act: -0.1700
Data Index: 8082415 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.9708. Min Act: -0.1700
Data Index: 3457407 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.9396. Min Act: -0.1700
Data Index: 2935327 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.9083. Min Act: -0.1700
Data Index: 6008366 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.9083. Min Act: -0.1700
Data Index: 5150258 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8770. Min Act: -0.1700
Data Index: 5037556 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 385109 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 5860746 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 4697764 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 5420129 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 5056311 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 3925500 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8770. Min Act: -0.1700
Data Index: 3980177 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 7649478 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 3782072 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 7620615 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8770. Min Act: -0.1700
Data Index: 3704839 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8458. Min Act: -0.1700
Data Index: 6476277 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0333. Min Range: -4.0333
Max Act: 3.8145. Min Act: -0.1700
Data Index: 5317486 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19