Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 260 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.7853. Min Act: -0.1700
Data Index: 4046009 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.7228. Min Act: -0.1700
Data Index: 1161906 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.6916. Min Act: -0.1700
Data Index: 7690103 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.6291. Min Act: -0.1700
Data Index: 1551916 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.6291. Min Act: -0.1700
Data Index: 6075320 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.5978. Min Act: -0.1700
Data Index: 7349941 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.5666. Min Act: -0.1700
Data Index: 5098167 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.5353. Min Act: -0.1700
Data Index: 339558 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.5353. Min Act: -0.1700
Data Index: 2470789 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.5041. Min Act: -0.1700
Data Index: 2887528 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.5041. Min Act: -0.1700
Data Index: 8157654 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.4728. Min Act: -0.1700
Data Index: 3112424 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.4416. Min Act: -0.1700
Data Index: 7265485 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.4728. Min Act: -0.1700
Data Index: 7659138 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.4416. Min Act: -0.1700
Data Index: 3315220 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.3791. Min Act: -0.1700
Data Index: 4187048 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.4103. Min Act: -0.1700
Data Index: 882895 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.3791. Min Act: -0.1700
Data Index: 1697711 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.4103. Min Act: -0.1700
Data Index: 2525837 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7853. Min Range: -6.7853
Max Act: 6.3478. Min Act: -0.1700
Data Index: 4514855 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19