Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1237 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.2167. Min Act: -0.1700
Data Index: 4993230 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1991. Min Act: -0.1700
Data Index: 8328041 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1815. Min Act: -0.1700
Data Index: 2664796 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1727. Min Act: -0.1700
Data Index: 8354010 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1639. Min Act: -0.1700
Data Index: 6346635 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1463. Min Act: -0.1700
Data Index: 4055309 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1288. Min Act: -0.1700
Data Index: 5628714 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1288. Min Act: -0.1700
Data Index: 80235 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1288. Min Act: -0.1700
Data Index: 2290933 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1200. Min Act: -0.1700
Data Index: 1806290 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1112. Min Act: -0.1700
Data Index: 2459777 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1025. Min Act: -0.1700
Data Index: 7657013 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1025. Min Act: -0.1700
Data Index: 3864709 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1025. Min Act: -0.1700
Data Index: 909766 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.0937. Min Act: -0.1700
Data Index: 4978852 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.0937. Min Act: -0.1700
Data Index: 4205796 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.0937. Min Act: -0.1700
Data Index: 1449578 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.0937. Min Act: -0.1700
Data Index: 4036875 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.1025. Min Act: -0.1700
Data Index: 4758711 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2167. Min Range: -1.2167
Max Act: 1.0937. Min Act: -0.1700
Data Index: 6588660 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19