Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.8241. Min Act: -0.1700
Data Index: 5915993 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.7304. Min Act: -0.1700
Data Index: 2398578 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6679. Min Act: -0.1700
Data Index: 4863149 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6991. Min Act: -0.1700
Data Index: 5026759 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6991. Min Act: -0.1700
Data Index: 5404094 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6679. Min Act: -0.1700
Data Index: 7591657 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6366. Min Act: -0.1700
Data Index: 484269 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6366. Min Act: -0.1700
Data Index: 7204882 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6054. Min Act: -0.1700
Data Index: 1957436 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6054. Min Act: -0.1700
Data Index: 6139673 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.6054. Min Act: -0.1700
Data Index: 4227072 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.5741. Min Act: -0.1700
Data Index: 5417670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.5429. Min Act: -0.1700
Data Index: 4193722 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.5741. Min Act: -0.1700
Data Index: 885678 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.5429. Min Act: -0.1700
Data Index: 6806201 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.5116. Min Act: -0.1700
Data Index: 4914215 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.5429. Min Act: -0.1700
Data Index: 3928524 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.5116. Min Act: -0.1700
Data Index: 6742328 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.4804. Min Act: -0.1700
Data Index: 885680 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8241. Min Range: -4.8241
Max Act: 4.5429. Min Act: -0.1700
Data Index: 6409000 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19