Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5182 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2451. Min Range: -6.2451
Max Act: 6.2451. Min Act: -0.1700
Data Index: 2947375 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2451. Min Range: -6.2451
Max Act: 6.0576. Min Act: -0.1700
Data Index: 4691567 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8701. Min Act: -0.1700
Data Index: 4424586 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.9013. Min Act: -0.1700
Data Index: 3197986 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8701. Min Act: -0.1700
Data Index: 4141809 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8701. Min Act: -0.1700
Data Index: 8617844 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8701. Min Act: -0.1700
Data Index: 8021019 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8388. Min Act: -0.1700
Data Index: 8446015 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8388. Min Act: -0.1700
Data Index: 4348610 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8388. Min Act: -0.1700
Data Index: 6731314 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8388. Min Act: -0.1700
Data Index: 4757144 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8388. Min Act: -0.1700
Data Index: 1528004 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 3508346 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 23181 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.8076. Min Act: -0.1700
Data Index: 5202357 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7763. Min Act: -0.1700
Data Index: 8214661 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7763. Min Act: -0.1700
Data Index: 8163533 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7763. Min Act: -0.1700
Data Index: 3771608 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7451. Min Act: -0.1700
Data Index: 423886 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2451. Min Range: -6.2451
Max Act: 5.7451. Min Act: -0.1700
Data Index: 4813798 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19