Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.5222. Min Act: -0.1700
Data Index: 7790556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.3660. Min Act: -0.1700
Data Index: 4786383 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.3347. Min Act: -0.1700
Data Index: 4932713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.3035. Min Act: -0.1700
Data Index: 6678189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.3035. Min Act: -0.1700
Data Index: 6175110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2722. Min Act: -0.1700
Data Index: 3223769 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2410. Min Act: -0.1700
Data Index: 5507974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2410. Min Act: -0.1700
Data Index: 227277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2410. Min Act: -0.1700
Data Index: 1836139 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2410. Min Act: -0.1700
Data Index: 975930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2410. Min Act: -0.1700
Data Index: 5719439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2097. Min Act: -0.1700
Data Index: 4196782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2097. Min Act: -0.1700
Data Index: 14190 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2097. Min Act: -0.1700
Data Index: 2047327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2097. Min Act: -0.1700
Data Index: 7581803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2097. Min Act: -0.1700
Data Index: 2105665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2097. Min Act: -0.1700
Data Index: 4372743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2097. Min Act: -0.1700
Data Index: 6728556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.2097. Min Act: -0.1700
Data Index: 528771 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5222. Min Range: -4.5222
Max Act: 4.1472. Min Act: -0.1700
Data Index: 48391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19