Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.6038. Min Act: -0.1700
Data Index: 4687797 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.5101. Min Act: -0.1700
Data Index: 5664435 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.5101. Min Act: -0.1700
Data Index: 1571842 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.4788. Min Act: -0.1700
Data Index: 7867256 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.4476. Min Act: -0.1700
Data Index: 75950 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.4163. Min Act: -0.1700
Data Index: 3817515 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.4163. Min Act: -0.1700
Data Index: 5966392 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.4163. Min Act: -0.1700
Data Index: 5836686 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.4476. Min Act: -0.1700
Data Index: 728074 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.3851. Min Act: -0.1700
Data Index: 6620126 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.3851. Min Act: -0.1700
Data Index: 2574212 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.3851. Min Act: -0.1700
Data Index: 70601 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.3851. Min Act: -0.1700
Data Index: 5966395 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.3538. Min Act: -0.1700
Data Index: 5866143 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.3226. Min Act: -0.1700
Data Index: 5975377 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.3226. Min Act: -0.1700
Data Index: 984995 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.3226. Min Act: -0.1700
Data Index: 3148910 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.2913. Min Act: -0.1700
Data Index: 4084097 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.2913. Min Act: -0.1700
Data Index: 4253494 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6038. Min Range: -5.6038
Max Act: 5.2913. Min Act: -0.1700
Data Index: 4522163 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19