Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4174. Min Range: -8.4174
Max Act: 8.4174. Min Act: -0.1700
Data Index: 8746779 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4174. Min Range: -8.4174
Max Act: 8.2299. Min Act: -0.1700
Data Index: 1328103 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4174. Min Range: -8.4174
Max Act: 8.1049. Min Act: -0.1700
Data Index: 4888208 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4174. Min Range: -8.4174
Max Act: 8.0424. Min Act: -0.1700
Data Index: 9612 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4174. Min Range: -8.4174
Max Act: 8.0424. Min Act: -0.1700
Data Index: 5728243 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4174. Min Range: -8.4174
Max Act: 8.0424. Min Act: -0.1700
Data Index: 7802128 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.8549. Min Act: -0.1700
Data Index: 1747054 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.8549. Min Act: -0.1700
Data Index: 4189040 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.8549. Min Act: -0.1700
Data Index: 6103148 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.7924. Min Act: -0.1700
Data Index: 5510363 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.7924. Min Act: -0.1700
Data Index: 5084335 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.7299. Min Act: -0.1700
Data Index: 6801911 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.7299. Min Act: -0.1700
Data Index: 2217914 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.7299. Min Act: -0.1700
Data Index: 2423596 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.6987. Min Act: -0.1700
Data Index: 6610363 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.6362. Min Act: -0.1700
Data Index: 1544327 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.6362. Min Act: -0.1700
Data Index: 3160727 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.6049. Min Act: -0.1700
Data Index: 6828697 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.6049. Min Act: -0.1700
Data Index: 3991407 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4174. Min Range: -8.4174
Max Act: 7.5737. Min Act: -0.1700
Data Index: 1065081 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19