Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0790. Min Range: -7.0790
Max Act: 7.0790. Min Act: -0.1700
Data Index: 3631851 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.9853. Min Act: -0.1700
Data Index: 1277358 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.8915. Min Act: -0.1700
Data Index: 8396370 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.4853. Min Act: -0.1700
Data Index: 5951242 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.4228. Min Act: -0.1700
Data Index: 758814 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.3915. Min Act: -0.1700
Data Index: 2292550 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.3915. Min Act: -0.1700
Data Index: 5045128 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.3290. Min Act: -0.1700
Data Index: 3545832 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.3290. Min Act: -0.1700
Data Index: 6554571 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2978. Min Act: -0.1700
Data Index: 4879713 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2978. Min Act: -0.1700
Data Index: 7754065 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2978. Min Act: -0.1700
Data Index: 6655416 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2978. Min Act: -0.1700
Data Index: 3987230 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2665. Min Act: -0.1700
Data Index: 6363394 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2665. Min Act: -0.1700
Data Index: 1998841 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2353. Min Act: -0.1700
Data Index: 2202326 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2353. Min Act: -0.1700
Data Index: 663872 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2353. Min Act: -0.1700
Data Index: 5966583 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2040. Min Act: -0.1700
Data Index: 1588099 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0790. Min Range: -7.0790
Max Act: 6.2040. Min Act: -0.1700
Data Index: 3035112 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19