Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5829 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.6005. Min Act: -0.1700
Data Index: 5617201 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.2880. Min Act: -0.1700
Data Index: 5690347 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.2255. Min Act: -0.1700
Data Index: 3957131 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.1630. Min Act: -0.1700
Data Index: 2010170 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.1317. Min Act: -0.1700
Data Index: 4673582 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.1317. Min Act: -0.1700
Data Index: 7922260 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.1317. Min Act: -0.1700
Data Index: 5384518 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.0692. Min Act: -0.1700
Data Index: 6980890 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.0692. Min Act: -0.1700
Data Index: 3483420 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.0692. Min Act: -0.1700
Data Index: 7884887 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6005. Min Range: -6.6005
Max Act: 6.0067. Min Act: -0.1700
Data Index: 7233734 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 5411709 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.9442. Min Act: -0.1700
Data Index: 7342605 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.9442. Min Act: -0.1700
Data Index: 5236458 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 8138031 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 1506765 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 6318356 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.9130. Min Act: -0.1700
Data Index: 1297272 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.8817. Min Act: -0.1700
Data Index: 5789617 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6005. Min Range: -6.6005
Max Act: 5.8817. Min Act: -0.1700
Data Index: 1977845 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19