Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.7391. Min Act: -0.1700
Data Index: 5579764 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.7078. Min Act: -0.1700
Data Index: 5825782 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.7078. Min Act: -0.1700
Data Index: 4001482 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.6766. Min Act: -0.1700
Data Index: 2813068 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.6453. Min Act: -0.1700
Data Index: 5218541 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.6141. Min Act: -0.1700
Data Index: 4195606 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.6453. Min Act: -0.1700
Data Index: 508161 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.6141. Min Act: -0.1700
Data Index: 875512 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.5828. Min Act: -0.1700
Data Index: 6828061 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.5828. Min Act: -0.1700
Data Index: 3695921 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.5203. Min Act: -0.1700
Data Index: 1243311 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.5203. Min Act: -0.1700
Data Index: 2918519 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.5203. Min Act: -0.1700
Data Index: 5883343 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.4891. Min Act: -0.1700
Data Index: 6259098 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.4578. Min Act: -0.1700
Data Index: 2551834 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.3953. Min Act: -0.1700
Data Index: 3169369 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.4266. Min Act: -0.1700
Data Index: 4989617 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.4266. Min Act: -0.1700
Data Index: 6104241 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.3953. Min Act: -0.1700
Data Index: 2347654 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7391. Min Range: -5.7391
Max Act: 5.4266. Min Act: -0.1700
Data Index: 5500543 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19