Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1117 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.9470. Min Act: -0.1700
Data Index: 2979057 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.8532. Min Act: -0.1700
Data Index: 3373885 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.8219. Min Act: -0.1700
Data Index: 3571064 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.7906. Min Act: -0.1700
Data Index: 8280689 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.7437. Min Act: -0.1700
Data Index: 6550957 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.7124. Min Act: -0.1700
Data Index: 1573844 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.7124. Min Act: -0.1700
Data Index: 3571065 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6968. Min Act: -0.1700
Data Index: 1882715 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.7124. Min Act: -0.1700
Data Index: 2945951 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.7124. Min Act: -0.1700
Data Index: 3830535 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6811. Min Act: -0.1700
Data Index: 3241196 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6811. Min Act: -0.1700
Data Index: 5492896 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6811. Min Act: -0.1700
Data Index: 7017796 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6655. Min Act: -0.1700
Data Index: 791363 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6811. Min Act: -0.1700
Data Index: 4471091 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6811. Min Act: -0.1700
Data Index: 4670256 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6655. Min Act: -0.1700
Data Index: 3699629 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6655. Min Act: -0.1700
Data Index: 3571059 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6498. Min Act: -0.1700
Data Index: 6704262 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9470. Min Range: -3.9470
Max Act: 3.6342. Min Act: -0.1700
Data Index: 655260 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19