Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2851 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0312. Min Range: -8.0312
Max Act: 8.0312. Min Act: -0.1697
Data Index: 7880769 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.9062. Min Act: -0.1700
Data Index: 7327990 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.9062. Min Act: -0.1621
Data Index: 7880738 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.8437. Min Act: -0.1616
Data Index: 3724661 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.8437. Min Act: -0.1700
Data Index: 415304 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.8437. Min Act: -0.1700
Data Index: 272089 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.8437. Min Act: -0.1697
Data Index: 6701225 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7812. Min Act: -0.1700
Data Index: 2037582 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7812. Min Act: -0.1696
Data Index: 889313 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7812. Min Act: -0.1700
Data Index: 1277692 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7812. Min Act: -0.1700
Data Index: 8367612 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7812. Min Act: -0.1646
Data Index: 889315 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7812. Min Act: -0.1700
Data Index: 4384383 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.6875. Min Act: -0.1700
Data Index: 104309 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7187. Min Act: -0.1650
Data Index: 889314 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7187. Min Act: -0.1455
Data Index: 3724677 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7187. Min Act: -0.1699
Data Index: 3724667 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.6875. Min Act: -0.1700
Data Index: 442256 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.6875. Min Act: -0.1699
Data Index: 7753492 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0312. Min Range: -8.0312
Max Act: 7.7187. Min Act: -0.1700
Data Index: 7880748 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19