Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5443. Min Range: -8.5443
Max Act: 8.5443. Min Act: -0.1700
Data Index: 3077973 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5443. Min Range: -8.5443
Max Act: 8.2943. Min Act: -0.1700
Data Index: 4370103 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5443. Min Range: -8.5443
Max Act: 8.1693. Min Act: -0.1700
Data Index: 5033449 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5443. Min Range: -8.5443
Max Act: 8.1693. Min Act: -0.1700
Data Index: 7208956 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5443. Min Range: -8.5443
Max Act: 8.1068. Min Act: -0.1700
Data Index: 2082080 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.9818. Min Act: -0.1700
Data Index: 3427461 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.8568. Min Act: -0.1700
Data Index: 7631938 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.8568. Min Act: -0.1700
Data Index: 7453950 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.7943. Min Act: -0.1700
Data Index: 6648105 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.7318. Min Act: -0.1700
Data Index: 6168383 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.7318. Min Act: -0.1700
Data Index: 1418261 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.7318. Min Act: -0.1700
Data Index: 6588469 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.7318. Min Act: -0.1700
Data Index: 660280 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.6693. Min Act: -0.1700
Data Index: 2647617 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.6068. Min Act: -0.1700
Data Index: 3316893 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.6068. Min Act: -0.1700
Data Index: 1518563 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.6068. Min Act: -0.1700
Data Index: 2647613 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.6068. Min Act: -0.1700
Data Index: 6443984 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.5443. Min Act: -0.1700
Data Index: 1861155 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5443. Min Range: -8.5443
Max Act: 7.5443. Min Act: -0.1700
Data Index: 5033450 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19