Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0880. Min Range: -6.0880
Max Act: 6.0880. Min Act: -0.1700
Data Index: 4386482 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.9942. Min Act: -0.1700
Data Index: 5448615 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.9630. Min Act: -0.1700
Data Index: 2649132 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.9317. Min Act: -0.1700
Data Index: 7891676 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.7755. Min Act: -0.1700
Data Index: 4461425 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.7755. Min Act: -0.1700
Data Index: 3051885 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5393273 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5567. Min Act: -0.1700
Data Index: 5247882 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5567. Min Act: -0.1700
Data Index: 6744511 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5567. Min Act: -0.1700
Data Index: 7045733 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5567. Min Act: -0.1700
Data Index: 8824212 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5880. Min Act: -0.1700
Data Index: 2910456 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5567. Min Act: -0.1700
Data Index: 3550870 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5255. Min Act: -0.1700
Data Index: 3614499 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5255. Min Act: -0.1700
Data Index: 8263216 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5255. Min Act: -0.1700
Data Index: 2543628 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.5255. Min Act: -0.1700
Data Index: 8672989 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.4942. Min Act: -0.1700
Data Index: 4685311 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.4942. Min Act: -0.1700
Data Index: 6506539 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0880. Min Range: -6.0880
Max Act: 5.4942. Min Act: -0.1700
Data Index: 83539 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19