Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.5282. Min Act: -0.1700
Data Index: 2712024 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.5282. Min Act: -0.1700
Data Index: 1927791 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.4344. Min Act: -0.1700
Data Index: 5092959 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.3094. Min Act: -0.1700
Data Index: 2917507 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.2782. Min Act: -0.1700
Data Index: 4611385 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.2157. Min Act: -0.1700
Data Index: 6307444 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.2157. Min Act: -0.1700
Data Index: 2201554 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.2157. Min Act: -0.1700
Data Index: 2788241 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.2157. Min Act: -0.1700
Data Index: 5770229 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.2157. Min Act: -0.1700
Data Index: 3594457 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.2157. Min Act: -0.1700
Data Index: 1854254 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.1844. Min Act: -0.1700
Data Index: 6173121 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.1532. Min Act: -0.1700
Data Index: 4264833 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.1532. Min Act: -0.1700
Data Index: 5327666 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.1219. Min Act: -0.1700
Data Index: 8782857 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.1844. Min Act: -0.1700
Data Index: 6941408 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.1532. Min Act: -0.1700
Data Index: 4302403 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.1532. Min Act: -0.1700
Data Index: 6911944 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.1219. Min Act: -0.1700
Data Index: 947156 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5282. Min Range: -4.5282
Max Act: 4.0906. Min Act: -0.1700
Data Index: 6563463 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19