Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.2286. Min Act: -0.1700
Data Index: 3410850 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.2286. Min Act: -0.1700
Data Index: 2590992 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.1036. Min Act: -0.1700
Data Index: 6985593 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.1661. Min Act: -0.1700
Data Index: 210155 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.2286. Min Act: -0.1700
Data Index: 7913096 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0411. Min Act: -0.1700
Data Index: 6943059 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.1036. Min Act: -0.1700
Data Index: 2590991 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.1036. Min Act: -0.1700
Data Index: 7287938 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0411. Min Act: -0.1700
Data Index: 3924112 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0411. Min Act: -0.1700
Data Index: 8053144 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0411. Min Act: -0.1700
Data Index: 2276826 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0411. Min Act: -0.1700
Data Index: 965589 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0411. Min Act: -0.1700
Data Index: 5896479 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0099. Min Act: -0.1700
Data Index: 6192794 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0099. Min Act: -0.1700
Data Index: 1169271 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2286. Min Range: -7.2286
Max Act: 7.0099. Min Act: -0.1700
Data Index: 1925633 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2286. Min Range: -7.2286
Max Act: 6.9786. Min Act: -0.1700
Data Index: 2688327 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2286. Min Range: -7.2286
Max Act: 6.9786. Min Act: -0.1700
Data Index: 3954452 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2286. Min Range: -7.2286
Max Act: 6.9786. Min Act: -0.1700
Data Index: 258695 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2286. Min Range: -7.2286
Max Act: 6.9786. Min Act: -0.1700
Data Index: 8244119 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19