Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2394 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.9906. Min Act: -0.1700
Data Index: 4261142 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0219. Min Range: -4.0219
Max Act: 4.0219. Min Act: -0.1700
Data Index: 263106 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.8968. Min Act: -0.1700
Data Index: 5270408 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.8812. Min Act: -0.1700
Data Index: 1940140 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.8655. Min Act: -0.1700
Data Index: 4800152 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.8186. Min Act: -0.1700
Data Index: 2611116 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.8030. Min Act: -0.1700
Data Index: 2446401 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.8030. Min Act: -0.1700
Data Index: 6252474 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7874. Min Act: -0.1700
Data Index: 5347905 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7874. Min Act: -0.1700
Data Index: 2491041 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7874. Min Act: -0.1700
Data Index: 1819255 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7874. Min Act: -0.1700
Data Index: 7244487 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7561. Min Act: -0.1700
Data Index: 6699223 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7404. Min Act: -0.1700
Data Index: 6373344 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7561. Min Act: -0.1700
Data Index: 1416711 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7248. Min Act: -0.1700
Data Index: 330212 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7404. Min Act: -0.1700
Data Index: 6659937 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7404. Min Act: -0.1700
Data Index: 2738752 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7404. Min Act: -0.1700
Data Index: 1518595 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0219. Min Range: -4.0219
Max Act: 3.7404. Min Act: -0.1700
Data Index: 506657 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19