Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4689 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.9594. Min Act: -0.1700
Data Index: 5173662 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.8031. Min Act: -0.1700
Data Index: 5641736 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.7719. Min Act: -0.1700
Data Index: 3529386 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.6781. Min Act: -0.1700
Data Index: 8801133 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.6156. Min Act: -0.1700
Data Index: 779967 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.5531. Min Act: -0.1700
Data Index: 6498500 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4594. Min Act: -0.1700
Data Index: 8115715 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.5219. Min Act: -0.1700
Data Index: 6806811 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4906. Min Act: -0.1700
Data Index: 4929839 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4906. Min Act: -0.1700
Data Index: 7053216 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4594. Min Act: -0.1700
Data Index: 6431533 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4594. Min Act: -0.1700
Data Index: 3390836 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4594. Min Act: -0.1700
Data Index: 6611985 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4594. Min Act: -0.1700
Data Index: 1411668 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4281. Min Act: -0.1700
Data Index: 9161 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4281. Min Act: -0.1700
Data Index: 1818272 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4281. Min Act: -0.1700
Data Index: 7824789 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.4281. Min Act: -0.1700
Data Index: 5473046 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.3969. Min Act: -0.1700
Data Index: 8178493 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9594. Min Range: -7.9594
Max Act: 7.3969. Min Act: -0.1700
Data Index: 2395266 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19