Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2938 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.6808. Min Act: -0.1700
Data Index: 411104 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.6495. Min Act: -0.1700
Data Index: 2752317 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.6025. Min Act: -0.1700
Data Index: 3230478 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.5869. Min Act: -0.1700
Data Index: 7019182 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.5399. Min Act: -0.1700
Data Index: 4617545 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.5399. Min Act: -0.1700
Data Index: 2309128 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.5086. Min Act: -0.1700
Data Index: 3271081 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.5086. Min Act: -0.1700
Data Index: 7783109 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4773. Min Act: -0.1700
Data Index: 8160495 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4929. Min Act: -0.1700
Data Index: 4798543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4773. Min Act: -0.1700
Data Index: 583050 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4616. Min Act: -0.1700
Data Index: 6238673 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4773. Min Act: -0.1700
Data Index: 2513509 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4616. Min Act: -0.1700
Data Index: 6317083 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4616. Min Act: -0.1700
Data Index: 2651196 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4773. Min Act: -0.1700
Data Index: 7746160 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4616. Min Act: -0.1700
Data Index: 2761353 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4459. Min Act: -0.1700
Data Index: 6323952 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4459. Min Act: -0.1700
Data Index: 434262 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6808. Min Range: -3.6808
Max Act: 3.4459. Min Act: -0.1700
Data Index: 1700941 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19