Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2340 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6064. Min Range: -7.6064
Max Act: 7.6064. Min Act: -0.1700
Data Index: 1559756 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6064. Min Range: -7.6064
Max Act: 7.4814. Min Act: -0.1700
Data Index: 6210788 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6064. Min Range: -7.6064
Max Act: 7.2627. Min Act: -0.1700
Data Index: 7796586 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6064. Min Range: -7.6064
Max Act: 7.1064. Min Act: -0.1700
Data Index: 7524201 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.9814. Min Act: -0.1700
Data Index: 2184540 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.8877. Min Act: -0.1700
Data Index: 1169356 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.8564. Min Act: -0.1700
Data Index: 799103 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.8252. Min Act: -0.1700
Data Index: 5469797 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.8252. Min Act: -0.1700
Data Index: 2514685 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.7939. Min Act: -0.1700
Data Index: 1365855 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.7939. Min Act: -0.1700
Data Index: 8529305 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.7627. Min Act: -0.1700
Data Index: 8129780 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.7314. Min Act: -0.1700
Data Index: 6343959 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.7002. Min Act: -0.1700
Data Index: 7355410 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.7002. Min Act: -0.1700
Data Index: 4904630 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.7002. Min Act: -0.1700
Data Index: 7834391 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.6377. Min Act: -0.1700
Data Index: 7109769 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.6689. Min Act: -0.1700
Data Index: 6749667 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.6377. Min Act: -0.1700
Data Index: 7036465 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6064. Min Range: -7.6064
Max Act: 6.6689. Min Act: -0.1700
Data Index: 771700 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19