Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1067 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.5222. Min Act: -0.1700
Data Index: 3622937 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.4285. Min Act: -0.1700
Data Index: 3405370 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3972. Min Act: -0.1700
Data Index: 3198121 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3972. Min Act: -0.1700
Data Index: 1635265 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3347. Min Act: -0.1700
Data Index: 1546559 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3660. Min Act: -0.1700
Data Index: 5689350 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3972. Min Act: -0.1700
Data Index: 3158345 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3347. Min Act: -0.1700
Data Index: 1061001 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3660. Min Act: -0.1700
Data Index: 3562064 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3035. Min Act: -0.1700
Data Index: 6154828 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3035. Min Act: -0.1700
Data Index: 2364417 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2722. Min Act: -0.1700
Data Index: 8640299 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2410. Min Act: -0.1700
Data Index: 6162672 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2097. Min Act: -0.1700
Data Index: 4349729 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2097. Min Act: -0.1700
Data Index: 1766774 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2097. Min Act: -0.1700
Data Index: 3926480 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2097. Min Act: -0.1700
Data Index: 3176191 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2097. Min Act: -0.1700
Data Index: 2904478 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.1472. Min Act: -0.1700
Data Index: 6035770 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.1785. Min Act: -0.1700
Data Index: 8017713 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19