Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4302 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1694. Min Range: -12.1694
Max Act: 12.1694. Min Act: -0.1700
Data Index: 7954209 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.9194. Min Act: -0.1700
Data Index: 655816 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.9194. Min Act: -0.1700
Data Index: 4650116 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.7944. Min Act: -0.1700
Data Index: 7703293 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.7319. Min Act: -0.1700
Data Index: 3840779 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.6069. Min Act: -0.1700
Data Index: 2656650 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.6069. Min Act: -0.1700
Data Index: 8157579 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.5444. Min Act: -0.1700
Data Index: 7546081 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.5444. Min Act: -0.1700
Data Index: 7467596 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.4819. Min Act: -0.1700
Data Index: 2014872 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.4194. Min Act: -0.1700
Data Index: 944035 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.4194. Min Act: -0.1700
Data Index: 3833137 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.4194. Min Act: -0.1700
Data Index: 6656678 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.4194. Min Act: -0.1700
Data Index: 5387806 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.3569. Min Act: -0.1700
Data Index: 3309261 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.2944. Min Act: -0.1700
Data Index: 2164199 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.2944. Min Act: -0.1700
Data Index: 4520550 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.2944. Min Act: -0.1700
Data Index: 550200 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.2319. Min Act: -0.1700
Data Index: 5277698 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1694. Min Range: -12.1694
Max Act: 11.2319. Min Act: -0.1700
Data Index: 4144328 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19