Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4184 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.4709. Min Act: -0.1700
Data Index: 2731900 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.3147. Min Act: -0.1700
Data Index: 6345423 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.2522. Min Act: -0.1700
Data Index: 8049444 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.0959. Min Act: -0.1700
Data Index: 7381022 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.0647. Min Act: -0.1700
Data Index: 536528 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.0334. Min Act: -0.1700
Data Index: 4938945 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.0334. Min Act: -0.1700
Data Index: 5827924 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9709. Min Act: -0.1700
Data Index: 6345387 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9709. Min Act: -0.1700
Data Index: 1384165 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4709. Min Range: -6.4709
Max Act: 6.0022. Min Act: -0.1700
Data Index: 7105980 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9397. Min Act: -0.1700
Data Index: 4633664 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9709. Min Act: -0.1700
Data Index: 527744 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.9084. Min Act: -0.1700
Data Index: 828290 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8772. Min Act: -0.1700
Data Index: 2758295 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8772. Min Act: -0.1700
Data Index: 8773155 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8459. Min Act: -0.1700
Data Index: 2780951 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8772. Min Act: -0.1700
Data Index: 7019903 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8772. Min Act: -0.1700
Data Index: 6654887 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8772. Min Act: -0.1700
Data Index: 7557514 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4709. Min Range: -6.4709
Max Act: 5.8772. Min Act: -0.1700
Data Index: 7487898 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19