Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4752 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0418. Min Range: -6.0418
Max Act: 6.0418. Min Act: -0.1700
Data Index: 3662381 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0418. Min Range: -6.0418
Max Act: 6.0105. Min Act: -0.1700
Data Index: 2266493 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.8230. Min Act: -0.1700
Data Index: 7991622 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.7605. Min Act: -0.1700
Data Index: 4915738 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.6980. Min Act: -0.1700
Data Index: 48093 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.6980. Min Act: -0.1700
Data Index: 6706619 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.6980. Min Act: -0.1700
Data Index: 1249492 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.6668. Min Act: -0.1700
Data Index: 2436797 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.6355. Min Act: -0.1700
Data Index: 2656284 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.6043. Min Act: -0.1700
Data Index: 4116677 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.6043. Min Act: -0.1700
Data Index: 6860252 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5730. Min Act: -0.1700
Data Index: 8092213 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5730. Min Act: -0.1700
Data Index: 3187958 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5418. Min Act: -0.1700
Data Index: 5447129 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5730. Min Act: -0.1700
Data Index: 7852041 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5730. Min Act: -0.1700
Data Index: 872653 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5105. Min Act: -0.1700
Data Index: 3561896 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5418. Min Act: -0.1700
Data Index: 2305465 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5418. Min Act: -0.1700
Data Index: 3911050 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0418. Min Range: -6.0418
Max Act: 5.5418. Min Act: -0.1700
Data Index: 3545643 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19