Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4115. Min Range: -7.4115
Max Act: 7.4115. Min Act: -0.1700
Data Index: 7421737 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4115. Min Range: -7.4115
Max Act: 7.2553. Min Act: -0.1700
Data Index: 6627483 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4115. Min Range: -7.4115
Max Act: 7.1615. Min Act: -0.1700
Data Index: 2254380 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4115. Min Range: -7.4115
Max Act: 7.0678. Min Act: -0.1700
Data Index: 938526 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4115. Min Range: -7.4115
Max Act: 7.0365. Min Act: -0.1700
Data Index: 3114120 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.9740. Min Act: -0.1700
Data Index: 2680367 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.9428. Min Act: -0.1700
Data Index: 5706720 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.9428. Min Act: -0.1700
Data Index: 6223323 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.9428. Min Act: -0.1700
Data Index: 1018620 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.9428. Min Act: -0.1700
Data Index: 5133557 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.9428. Min Act: -0.1700
Data Index: 8250088 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.9115. Min Act: -0.1700
Data Index: 5883074 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.9115. Min Act: -0.1700
Data Index: 701693 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.8803. Min Act: -0.1700
Data Index: 6876723 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.8803. Min Act: -0.1700
Data Index: 1020005 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.8490. Min Act: -0.1700
Data Index: 5989289 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.8490. Min Act: -0.1700
Data Index: 4851802 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.8490. Min Act: -0.1700
Data Index: 3389150 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.8490. Min Act: -0.1700
Data Index: 1132200 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4115. Min Range: -7.4115
Max Act: 6.8490. Min Act: -0.1700
Data Index: 6960009 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19