Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1507 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.8830. Min Act: -0.1700
Data Index: 1222279 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.8830. Min Act: -0.1700
Data Index: 3101579 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.8205. Min Act: -0.1700
Data Index: 6750157 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.6955. Min Act: -0.1700
Data Index: 5259950 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.5705. Min Act: -0.1700
Data Index: 3304572 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.5705. Min Act: -0.1700
Data Index: 6833561 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.4455. Min Act: -0.1700
Data Index: 5104821 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.4455. Min Act: -0.1700
Data Index: 5259948 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.4455. Min Act: -0.1700
Data Index: 1019013 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.4143. Min Act: -0.1700
Data Index: 3358691 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3830. Min Act: -0.1700
Data Index: 5911850 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3830. Min Act: -0.1700
Data Index: 1865545 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3830. Min Act: -0.1700
Data Index: 4878685 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3830. Min Act: -0.1700
Data Index: 2733637 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3518. Min Act: -0.1700
Data Index: 4220460 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3830. Min Act: -0.1700
Data Index: 7893537 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3205. Min Act: -0.1700
Data Index: 5715643 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3205. Min Act: -0.1700
Data Index: 246669 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.3205. Min Act: -0.1700
Data Index: 1565120 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8830. Min Range: -7.8830
Max Act: 7.2580. Min Act: -0.1700
Data Index: 5376746 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19