Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8585. Min Range: -7.8585
Max Act: 7.8585. Min Act: -0.1700
Data Index: 5929615 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.9210. Min Act: -0.1700
Data Index: 1113449 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.8585. Min Act: -0.1700
Data Index: 6853813 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.8585. Min Act: -0.1700
Data Index: 7199157 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.7648. Min Act: -0.1700
Data Index: 1618120 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.7335. Min Act: -0.1700
Data Index: 521941 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.6710. Min Act: -0.1700
Data Index: 1377758 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.6398. Min Act: -0.1700
Data Index: 1467899 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.6085. Min Act: -0.1700
Data Index: 5418482 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.6085. Min Act: -0.1700
Data Index: 1933972 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.5773. Min Act: -0.1700
Data Index: 3149504 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.6085. Min Act: -0.1700
Data Index: 3285613 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.5773. Min Act: -0.1700
Data Index: 7057739 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.5773. Min Act: -0.1700
Data Index: 3665645 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.5460. Min Act: -0.1700
Data Index: 231024 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.5773. Min Act: -0.1700
Data Index: 7066279 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.5773. Min Act: -0.1700
Data Index: 7805935 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.5460. Min Act: -0.1700
Data Index: 3046471 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.4835. Min Act: -0.1700
Data Index: 6735291 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8585. Min Range: -7.8585
Max Act: 6.4835. Min Act: -0.1700
Data Index: 3209250 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19