Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2397 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.8723. Min Act: -0.1700
Data Index: 6963072 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6848. Min Act: -0.1700
Data Index: 6074722 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.8098. Min Act: -0.1700
Data Index: 8704321 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6848. Min Act: -0.1700
Data Index: 1649046 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6848. Min Act: -0.1700
Data Index: 754325 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6848. Min Act: -0.1700
Data Index: 6655344 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6848. Min Act: -0.1700
Data Index: 8351583 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6848. Min Act: -0.1700
Data Index: 8684164 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6848. Min Act: -0.1700
Data Index: 3179341 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6223. Min Act: -0.1700
Data Index: 2436835 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6848. Min Act: -0.1700
Data Index: 6864944 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6223. Min Act: -0.1700
Data Index: 8622496 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6223. Min Act: -0.1700
Data Index: 4362124 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6223. Min Act: -0.1700
Data Index: 7462777 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6223. Min Act: -0.1700
Data Index: 4123944 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6223. Min Act: -0.1700
Data Index: 1690365 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6223. Min Act: -0.1700
Data Index: 7329193 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.6223. Min Act: -0.1700
Data Index: 1945138 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.5598. Min Act: -0.1700
Data Index: 7095041 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8723. Min Range: -9.8723
Max Act: 9.4973. Min Act: -0.1700
Data Index: 4012710 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19