Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.4441. Min Act: -0.1700
Data Index: 2101315 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.3191. Min Act: -0.1700
Data Index: 3462101 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.2566. Min Act: -0.1700
Data Index: 1835271 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.2566. Min Act: -0.1700
Data Index: 560247 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.1941. Min Act: -0.1700
Data Index: 3707509 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.1941. Min Act: -0.1700
Data Index: 3820345 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.2566. Min Act: -0.1700
Data Index: 8678951 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.1941. Min Act: -0.1700
Data Index: 8165759 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.0691. Min Act: -0.1700
Data Index: 7878858 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4441. Min Range: -9.4441
Max Act: 9.0066. Min Act: -0.1700
Data Index: 3511753 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.9441. Min Act: -0.1700
Data Index: 5541041 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.8816. Min Act: -0.1700
Data Index: 4759266 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.8816. Min Act: -0.1700
Data Index: 4415072 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.9441. Min Act: -0.1700
Data Index: 4576020 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.8816. Min Act: -0.1700
Data Index: 4170256 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.8816. Min Act: -0.1700
Data Index: 8076837 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.8816. Min Act: -0.1700
Data Index: 5158365 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.8191. Min Act: -0.1700
Data Index: 7622460 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.8191. Min Act: -0.1700
Data Index: 3264504 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4441. Min Range: -9.4441
Max Act: 8.8191. Min Act: -0.1700
Data Index: 3292520 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19