Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 872 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2823. Min Range: -8.2823
Max Act: 8.2823. Min Act: -0.1700
Data Index: 4683146 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2823. Min Range: -8.2823
Max Act: 8.0948. Min Act: -0.1700
Data Index: 7928782 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.9698. Min Act: -0.1700
Data Index: 7288771 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.9073. Min Act: -0.1700
Data Index: 4191843 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.8136. Min Act: -0.1700
Data Index: 6514828 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.7198. Min Act: -0.1700
Data Index: 3863568 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.7198. Min Act: -0.1700
Data Index: 3275944 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.6886. Min Act: -0.1700
Data Index: 8185499 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.6573. Min Act: -0.1700
Data Index: 1089054 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.6261. Min Act: -0.1700
Data Index: 7392791 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5948. Min Act: -0.1700
Data Index: 7186386 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5948. Min Act: -0.1700
Data Index: 5288809 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5948. Min Act: -0.1700
Data Index: 8694057 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5636. Min Act: -0.1700
Data Index: 7910066 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5636. Min Act: -0.1700
Data Index: 2706200 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5323. Min Act: -0.1700
Data Index: 4521258 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5323. Min Act: -0.1700
Data Index: 6767056 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5323. Min Act: -0.1700
Data Index: 1169245 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.5011. Min Act: -0.1700
Data Index: 3571180 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2823. Min Range: -8.2823
Max Act: 7.4698. Min Act: -0.1700
Data Index: 1100762 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19