Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3489 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.7616. Min Act: -0.1700
Data Index: 4164553 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.6054. Min Act: -0.1700
Data Index: 1091507 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.5429. Min Act: -0.1700
Data Index: 7019991 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.5741. Min Act: -0.1700
Data Index: 2148040 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.4804. Min Act: -0.1700
Data Index: 1059121 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.4804. Min Act: -0.1700
Data Index: 3753138 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.4179. Min Act: -0.1700
Data Index: 3058221 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.3554. Min Act: -0.1700
Data Index: 3040382 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.3241. Min Act: -0.1700
Data Index: 6469601 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.3554. Min Act: -0.1700
Data Index: 2551654 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.2929. Min Act: -0.1700
Data Index: 7540441 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.2929. Min Act: -0.1700
Data Index: 7349557 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.1991. Min Act: -0.1700
Data Index: 422582 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.1991. Min Act: -0.1700
Data Index: 4628027 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.1679. Min Act: -0.1700
Data Index: 1754644 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.1679. Min Act: -0.1700
Data Index: 2302208 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.1679. Min Act: -0.1700
Data Index: 3467837 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.1679. Min Act: -0.1700
Data Index: 5111650 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.1679. Min Act: -0.1700
Data Index: 1178505 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7616. Min Range: -6.7616
Max Act: 6.1679. Min Act: -0.1700
Data Index: 6654180 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19