Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5760 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.8177. Min Act: -0.1700
Data Index: 171665 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.6927. Min Act: -0.1700
Data Index: 7600527 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.5677. Min Act: -0.1700
Data Index: 1815064 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.5677. Min Act: -0.1700
Data Index: 2240948 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.5677. Min Act: -0.1700
Data Index: 5208822 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.5052. Min Act: -0.1700
Data Index: 521965 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.4739. Min Act: -0.1700
Data Index: 1024382 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.4427. Min Act: -0.1700
Data Index: 5476099 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.4114. Min Act: -0.1700
Data Index: 4054590 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.4114. Min Act: -0.1700
Data Index: 7644267 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.4114. Min Act: -0.1700
Data Index: 7964647 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.3489. Min Act: -0.1700
Data Index: 4275309 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.3177. Min Act: -0.1700
Data Index: 4567772 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.3177. Min Act: -0.1700
Data Index: 4925390 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.2864. Min Act: -0.1700
Data Index: 1867986 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.2864. Min Act: -0.1700
Data Index: 5208821 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.3177. Min Act: -0.1700
Data Index: 4693677 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.2552. Min Act: -0.1700
Data Index: 5379557 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.1927. Min Act: -0.1700
Data Index: 3144224 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8177. Min Range: -7.8177
Max Act: 7.1614. Min Act: -0.1700
Data Index: 4564541 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19