Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4206 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.8241. Min Act: -0.1700
Data Index: 5414597 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.7615. Min Act: -0.1700
Data Index: 5310631 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.6990. Min Act: -0.1700
Data Index: 3090592 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.6990. Min Act: -0.1700
Data Index: 7729200 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.6364. Min Act: -0.1700
Data Index: 4702956 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5894. Min Act: -0.1700
Data Index: 3877400 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.6051. Min Act: -0.1700
Data Index: 4217856 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.6051. Min Act: -0.1700
Data Index: 2641773 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5738. Min Act: -0.1700
Data Index: 2304996 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5894. Min Act: -0.1700
Data Index: 2313540 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5738. Min Act: -0.1700
Data Index: 839336 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5112. Min Act: -0.1700
Data Index: 680969 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5268. Min Act: -0.1700
Data Index: 4195191 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5425. Min Act: -0.1700
Data Index: 5748434 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5112. Min Act: -0.1700
Data Index: 8039053 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.4955. Min Act: -0.1700
Data Index: 3270321 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5112. Min Act: -0.1700
Data Index: 218750 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5112. Min Act: -0.1700
Data Index: 8282292 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5425. Min Act: -0.1700
Data Index: 4899048 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8241. Min Range: -3.8241
Max Act: 3.5112. Min Act: -0.1700
Data Index: 2388248 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19