Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5551 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6476. Min Range: -6.6476
Max Act: 6.6476. Min Act: -0.1700
Data Index: 6724395 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6476. Min Range: -6.6476
Max Act: 6.2726. Min Act: -0.1700
Data Index: 2605332 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.8038. Min Act: -0.1700
Data Index: 572846 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.6788. Min Act: -0.1700
Data Index: 408114 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.6788. Min Act: -0.1700
Data Index: 6123989 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.6476. Min Act: -0.1700
Data Index: 8743720 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.5851. Min Act: -0.1700
Data Index: 5717034 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.5538. Min Act: -0.1700
Data Index: 6108631 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.5538. Min Act: -0.1700
Data Index: 89916 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.5226. Min Act: -0.1700
Data Index: 3898563 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.4913. Min Act: -0.1700
Data Index: 5829688 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.4601. Min Act: -0.1700
Data Index: 5879116 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.4601. Min Act: -0.1700
Data Index: 4237954 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.4288. Min Act: -0.1700
Data Index: 3814114 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.3976. Min Act: -0.1700
Data Index: 720568 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.4288. Min Act: -0.1700
Data Index: 4302975 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.4288. Min Act: -0.1700
Data Index: 7645044 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.4288. Min Act: -0.1700
Data Index: 8342209 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.3976. Min Act: -0.1700
Data Index: 2543738 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6476. Min Range: -6.6476
Max Act: 5.3976. Min Act: -0.1700
Data Index: 7312350 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19