Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3223. Min Range: -7.3223
Max Act: 7.3223. Min Act: -0.1700
Data Index: 6657653 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3223. Min Range: -7.3223
Max Act: 7.2286. Min Act: -0.1700
Data Index: 3327256 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3223. Min Range: -7.3223
Max Act: 7.1661. Min Act: -0.1700
Data Index: 2458425 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3223. Min Range: -7.3223
Max Act: 7.1348. Min Act: -0.1700
Data Index: 2700414 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3223. Min Range: -7.3223
Max Act: 7.1036. Min Act: -0.1700
Data Index: 3777003 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3223. Min Range: -7.3223
Max Act: 7.0411. Min Act: -0.1700
Data Index: 3018294 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3223. Min Range: -7.3223
Max Act: 7.0098. Min Act: -0.1700
Data Index: 2162936 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.8223. Min Act: -0.1700
Data Index: 8465736 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.8536. Min Act: -0.1700
Data Index: 6504278 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.7911. Min Act: -0.1700
Data Index: 352347 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.7598. Min Act: -0.1700
Data Index: 1396385 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.7286. Min Act: -0.1700
Data Index: 1736629 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.7598. Min Act: -0.1700
Data Index: 2561753 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.7598. Min Act: -0.1700
Data Index: 6072178 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.7286. Min Act: -0.1700
Data Index: 4376240 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.6973. Min Act: -0.1700
Data Index: 4145680 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.6973. Min Act: -0.1700
Data Index: 632522 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.6348. Min Act: -0.1700
Data Index: 4425079 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.6973. Min Act: -0.1700
Data Index: 6218356 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3223. Min Range: -7.3223
Max Act: 6.6661. Min Act: -0.1700
Data Index: 6172323 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19