Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1841 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1906. Min Range: -7.1906
Max Act: 7.1906. Min Act: -0.1700
Data Index: 6271754 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1906. Min Range: -7.1906
Max Act: 7.0969. Min Act: -0.1700
Data Index: 4734910 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.8156. Min Act: -0.1700
Data Index: 394481 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.7844. Min Act: -0.1700
Data Index: 530058 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.7219. Min Act: -0.1700
Data Index: 7706520 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.7219. Min Act: -0.1700
Data Index: 4229265 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.6906. Min Act: -0.1700
Data Index: 4482754 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.6906. Min Act: -0.1700
Data Index: 3966232 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5656. Min Act: -0.1700
Data Index: 6681382 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5969. Min Act: -0.1700
Data Index: 1420693 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.6281. Min Act: -0.1700
Data Index: 3668991 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5969. Min Act: -0.1700
Data Index: 4372568 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5656. Min Act: -0.1700
Data Index: 6699247 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5656. Min Act: -0.1700
Data Index: 510069 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5969. Min Act: -0.1700
Data Index: 2000839 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5656. Min Act: -0.1700
Data Index: 5701570 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5344. Min Act: -0.1700
Data Index: 2455523 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5344. Min Act: -0.1700
Data Index: 7979311 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.4719. Min Act: -0.1700
Data Index: 2730808 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1906. Min Range: -7.1906
Max Act: 6.5344. Min Act: -0.1700
Data Index: 6391084 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19