Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4896 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.4728. Min Act: -0.1700
Data Index: 4090511 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.4416. Min Act: -0.1700
Data Index: 8545630 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.4103. Min Act: -0.1700
Data Index: 5956350 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.3791. Min Act: -0.1700
Data Index: 1497819 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.3791. Min Act: -0.1700
Data Index: 3927220 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.3166. Min Act: -0.1700
Data Index: 3983166 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.3478. Min Act: -0.1700
Data Index: 595309 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.3166. Min Act: -0.1700
Data Index: 6359377 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.3166. Min Act: -0.1700
Data Index: 693094 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2853. Min Act: -0.1700
Data Index: 6359372 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2541. Min Act: -0.1700
Data Index: 869224 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2853. Min Act: -0.1700
Data Index: 3562111 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2541. Min Act: -0.1700
Data Index: 3459589 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2853. Min Act: -0.1700
Data Index: 6777591 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2541. Min Act: -0.1700
Data Index: 1275691 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2541. Min Act: -0.1700
Data Index: 8251129 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2541. Min Act: -0.1700
Data Index: 6359380 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2541. Min Act: -0.1700
Data Index: 5282969 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2228. Min Act: -0.1700
Data Index: 5464438 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4728. Min Range: -5.4728
Max Act: 5.2228. Min Act: -0.1700
Data Index: 6359378 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19