Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1194 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.5174. Min Act: -0.1700
Data Index: 8696693 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.4237. Min Act: -0.1700
Data Index: 215517 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.4237. Min Act: -0.1700
Data Index: 5398197 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.3299. Min Act: -0.1700
Data Index: 3016358 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.3299. Min Act: -0.1700
Data Index: 5441026 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.2362. Min Act: -0.1700
Data Index: 2293478 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.2049. Min Act: -0.1700
Data Index: 3241368 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.2049. Min Act: -0.1700
Data Index: 8704992 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.1424. Min Act: -0.1700
Data Index: 110825 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.0799. Min Act: -0.1700
Data Index: 3547174 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.0799. Min Act: -0.1700
Data Index: 950295 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.1112. Min Act: -0.1700
Data Index: 78243 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.0174. Min Act: -0.1700
Data Index: 509687 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.0799. Min Act: -0.1700
Data Index: 4152952 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.0487. Min Act: -0.1700
Data Index: 885716 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.0174. Min Act: -0.1700
Data Index: 5121303 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5174. Min Range: -5.5174
Max Act: 5.0174. Min Act: -0.1700
Data Index: 7395137 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5174. Min Range: -5.5174
Max Act: 4.9862. Min Act: -0.1700
Data Index: 2917594 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5174. Min Range: -5.5174
Max Act: 4.9862. Min Act: -0.1700
Data Index: 4948887 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5174. Min Range: -5.5174
Max Act: 4.9862. Min Act: -0.1700
Data Index: 6263448 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19