Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1155 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0500. Min Range: -6.0500
Max Act: 6.0500. Min Act: -0.1700
Data Index: 7030009 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.9250. Min Act: -0.1700
Data Index: 2474647 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.8313. Min Act: -0.1700
Data Index: 6176946 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.7688. Min Act: -0.1700
Data Index: 1194917 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.7375. Min Act: -0.1700
Data Index: 4078748 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.6750. Min Act: -0.1700
Data Index: 474696 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.6438. Min Act: -0.1700
Data Index: 1422519 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.6125. Min Act: -0.1700
Data Index: 439589 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.5813. Min Act: -0.1700
Data Index: 3781576 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.4875. Min Act: -0.1700
Data Index: 6688271 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.4563. Min Act: -0.1700
Data Index: 1113894 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.4563. Min Act: -0.1700
Data Index: 2370581 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.4875. Min Act: -0.1700
Data Index: 4629658 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.4250. Min Act: -0.1700
Data Index: 624784 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.4250. Min Act: -0.1700
Data Index: 4827774 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.4250. Min Act: -0.1700
Data Index: 3803701 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.3938. Min Act: -0.1700
Data Index: 6035420 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.3938. Min Act: -0.1700
Data Index: 4920766 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.3938. Min Act: -0.1700
Data Index: 2567182 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0500. Min Range: -6.0500
Max Act: 5.3625. Min Act: -0.1700
Data Index: 828118 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19