Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.9552. Min Act: -0.1700
Data Index: 5536023 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.8302. Min Act: -0.1700
Data Index: 2388110 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.7990. Min Act: -0.1700
Data Index: 5308831 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.7677. Min Act: -0.1700
Data Index: 1500453 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.7052. Min Act: -0.1700
Data Index: 3346919 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.7365. Min Act: -0.1700
Data Index: 6211523 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.6115. Min Act: -0.1700
Data Index: 7622117 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.5177. Min Act: -0.1700
Data Index: 7646237 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4865. Min Act: -0.1700
Data Index: 7787786 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4865. Min Act: -0.1700
Data Index: 4268163 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4865. Min Act: -0.1700
Data Index: 7959941 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4865. Min Act: -0.1700
Data Index: 820353 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4865. Min Act: -0.1700
Data Index: 2404083 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4865. Min Act: -0.1700
Data Index: 5471352 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4865. Min Act: -0.1700
Data Index: 2548313 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4552. Min Act: -0.1700
Data Index: 2967647 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4552. Min Act: -0.1700
Data Index: 2545195 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4552. Min Act: -0.1700
Data Index: 1690605 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4552. Min Act: -0.1700
Data Index: 6528166 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9552. Min Range: -5.9552
Max Act: 5.4552. Min Act: -0.1700
Data Index: 7600182 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19