Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5151 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3183. Min Range: -9.3183
Max Act: 9.3183. Min Act: -0.1700
Data Index: 8180560 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3183. Min Range: -9.3183
Max Act: 9.1933. Min Act: -0.1700
Data Index: 6290385 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3183. Min Range: -9.3183
Max Act: 9.0058. Min Act: -0.1700
Data Index: 4976812 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.9433. Min Act: -0.1700
Data Index: 5702971 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.9433. Min Act: -0.1700
Data Index: 6652540 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.8808. Min Act: -0.1700
Data Index: 6577394 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.8808. Min Act: -0.1700
Data Index: 4983500 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.8808. Min Act: -0.1700
Data Index: 8535920 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.8808. Min Act: -0.1700
Data Index: 644502 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.8183. Min Act: -0.1700
Data Index: 3191833 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.7558. Min Act: -0.1700
Data Index: 6829065 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.7558. Min Act: -0.1700
Data Index: 8533593 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.7558. Min Act: -0.1700
Data Index: 3167933 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.7558. Min Act: -0.1700
Data Index: 3080880 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.7558. Min Act: -0.1700
Data Index: 2796463 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.7558. Min Act: -0.1700
Data Index: 2755098 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.6933. Min Act: -0.1700
Data Index: 3241934 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.6933. Min Act: -0.1700
Data Index: 1470064 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.6933. Min Act: -0.1700
Data Index: 7744485 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3183. Min Range: -9.3183
Max Act: 8.6308. Min Act: -0.1700
Data Index: 305039 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19