Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.6368. Min Act: -0.1700
Data Index: 1221176 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.4019. Min Act: -0.1700
Data Index: 6295934 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3862. Min Act: -0.1700
Data Index: 8545491 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3862. Min Act: -0.1700
Data Index: 1076551 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3706. Min Act: -0.1700
Data Index: 3803599 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3862. Min Act: -0.1700
Data Index: 7599729 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3706. Min Act: -0.1700
Data Index: 1251477 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3392. Min Act: -0.1700
Data Index: 7882505 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3235. Min Act: -0.1700
Data Index: 675736 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3235. Min Act: -0.1700
Data Index: 3736722 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2764. Min Act: -0.1700
Data Index: 1493438 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.3078. Min Act: -0.1700
Data Index: 957799 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2921. Min Act: -0.1700
Data Index: 8192978 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2764. Min Act: -0.1700
Data Index: 5262066 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2764. Min Act: -0.1700
Data Index: 3283277 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2450. Min Act: -0.1700
Data Index: 2675753 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2607. Min Act: -0.1700
Data Index: 2144271 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2293. Min Act: -0.1700
Data Index: 6007272 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2450. Min Act: -0.1700
Data Index: 3104448 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6368. Min Range: -3.6368
Max Act: 3.2293. Min Act: -0.1700
Data Index: 1765616 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19