Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 764 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.5773. Min Act: -0.1700
Data Index: 5059382 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.4363. Min Act: -0.1700
Data Index: 1930662 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.4050. Min Act: -0.1700
Data Index: 991598 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.4050. Min Act: -0.1700
Data Index: 2839061 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.4050. Min Act: -0.1700
Data Index: 621079 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3893. Min Act: -0.1700
Data Index: 1041994 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3893. Min Act: -0.1700
Data Index: 6003564 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3893. Min Act: -0.1700
Data Index: 2033905 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3580. Min Act: -0.1700
Data Index: 6763840 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3266. Min Act: -0.1700
Data Index: 2611252 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3423. Min Act: -0.1700
Data Index: 6978094 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3266. Min Act: -0.1700
Data Index: 2116196 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3266. Min Act: -0.1700
Data Index: 1540083 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3266. Min Act: -0.1700
Data Index: 1061030 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3109. Min Act: -0.1700
Data Index: 8679391 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3109. Min Act: -0.1700
Data Index: 2330426 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.3109. Min Act: -0.1700
Data Index: 5500033 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.2952. Min Act: -0.1700
Data Index: 4021694 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.2795. Min Act: -0.1700
Data Index: 1754269 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5773. Min Range: -3.5773
Max Act: 3.2795. Min Act: -0.1700
Data Index: 2711765 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19