Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.3443. Min Act: -0.1700
Data Index: 2205675 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.2193. Min Act: -0.1700
Data Index: 3261433 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.1256. Min Act: -0.1700
Data Index: 1079445 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.1568. Min Act: -0.1700
Data Index: 6558603 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.1256. Min Act: -0.1700
Data Index: 2170573 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.0631. Min Act: -0.1700
Data Index: 7231761 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3443. Min Range: -7.3443
Max Act: 7.0318. Min Act: -0.1700
Data Index: 5196064 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.9693. Min Act: -0.1700
Data Index: 3109410 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.9381. Min Act: -0.1700
Data Index: 1694322 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.9381. Min Act: -0.1700
Data Index: 7903609 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8756. Min Act: -0.1700
Data Index: 5988304 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8756. Min Act: -0.1700
Data Index: 379518 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8443. Min Act: -0.1700
Data Index: 5469979 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8756. Min Act: -0.1700
Data Index: 2599809 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8131. Min Act: -0.1700
Data Index: 2703832 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.8443. Min Act: -0.1700
Data Index: 3528391 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7818. Min Act: -0.1700
Data Index: 1694323 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7506. Min Act: -0.1700
Data Index: 2830755 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7193. Min Act: -0.1700
Data Index: 7744621 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3443. Min Range: -7.3443
Max Act: 6.7193. Min Act: -0.1700
Data Index: 3326460 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19