Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3307. Min Range: -8.3307
Max Act: 8.3307. Min Act: -0.1700
Data Index: 3238719 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.9557. Min Act: -0.1700
Data Index: 376314 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.8307. Min Act: -0.1700
Data Index: 1247189 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.8932. Min Act: -0.1700
Data Index: 3759206 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.8932. Min Act: -0.1700
Data Index: 8458308 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.8307. Min Act: -0.1700
Data Index: 38563 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.8307. Min Act: -0.1700
Data Index: 2431210 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7682. Min Act: -0.1700
Data Index: 4704423 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7682. Min Act: -0.1700
Data Index: 1068406 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7682. Min Act: -0.1700
Data Index: 1328663 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7682. Min Act: -0.1700
Data Index: 5041057 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7682. Min Act: -0.1700
Data Index: 5724334 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7682. Min Act: -0.1700
Data Index: 7398537 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7682. Min Act: -0.1700
Data Index: 3981517 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7057. Min Act: -0.1700
Data Index: 1712026 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7057. Min Act: -0.1700
Data Index: 8040191 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7057. Min Act: -0.1700
Data Index: 1283240 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7057. Min Act: -0.1700
Data Index: 5745987 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.7057. Min Act: -0.1700
Data Index: 4750759 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3307. Min Range: -8.3307
Max Act: 7.6432. Min Act: -0.1700
Data Index: 2647355 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19