Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5394 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1727. Min Range: -4.1727
Max Act: 4.1727. Min Act: -0.1700
Data Index: 576160 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1727. Min Range: -4.1727
Max Act: 4.1414. Min Act: -0.1700
Data Index: 5050742 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1727. Min Range: -4.1727
Max Act: 4.1102. Min Act: -0.1700
Data Index: 4277858 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1727. Min Range: -4.1727
Max Act: 4.0476. Min Act: -0.1700
Data Index: 6445447 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1727. Min Range: -4.1727
Max Act: 4.0476. Min Act: -0.1700
Data Index: 412824 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1727. Min Range: -4.1727
Max Act: 4.0476. Min Act: -0.1700
Data Index: 3659504 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1727. Min Range: -4.1727
Max Act: 4.0164. Min Act: -0.1700
Data Index: 1398999 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9539. Min Act: -0.1700
Data Index: 4010429 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9851. Min Act: -0.1700
Data Index: 714641 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9539. Min Act: -0.1700
Data Index: 714640 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9539. Min Act: -0.1700
Data Index: 7234419 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9851. Min Act: -0.1700
Data Index: 7929677 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9539. Min Act: -0.1700
Data Index: 8741562 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9226. Min Act: -0.1700
Data Index: 6092954 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.8913. Min Act: -0.1700
Data Index: 5505074 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.8913. Min Act: -0.1700
Data Index: 5330712 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9226. Min Act: -0.1700
Data Index: 2082210 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9226. Min Act: -0.1700
Data Index: 4584840 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9539. Min Act: -0.1700
Data Index: 7544876 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1727. Min Range: -4.1727
Max Act: 3.9226. Min Act: -0.1700
Data Index: 7124695 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19