Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0038. Min Range: -7.0038
Max Act: 7.0038. Min Act: -0.1700
Data Index: 3901893 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.4726. Min Act: -0.1700
Data Index: 3127097 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.4413. Min Act: -0.1700
Data Index: 7925490 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.4101. Min Act: -0.1700
Data Index: 2245971 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.4101. Min Act: -0.1700
Data Index: 7839857 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.3163. Min Act: -0.1700
Data Index: 872114 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.2538. Min Act: -0.1700
Data Index: 947143 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.2538. Min Act: -0.1700
Data Index: 6973808 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.2226. Min Act: -0.1700
Data Index: 808074 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.2226. Min Act: -0.1700
Data Index: 3145996 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 7731501 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.1288. Min Act: -0.1700
Data Index: 6570205 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.0976. Min Act: -0.1700
Data Index: 6023512 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.0976. Min Act: -0.1700
Data Index: 7622638 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.0976. Min Act: -0.1700
Data Index: 1944493 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.0663. Min Act: -0.1700
Data Index: 2339743 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.0663. Min Act: -0.1700
Data Index: 1380748 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.0663. Min Act: -0.1700
Data Index: 173799 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.0663. Min Act: -0.1700
Data Index: 6374219 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0038. Min Range: -7.0038
Max Act: 6.0663. Min Act: -0.1700
Data Index: 6889642 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19