Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.8315. Min Act: -0.1700
Data Index: 2736263 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.8003. Min Act: -0.1700
Data Index: 4712451 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.7690. Min Act: -0.1700
Data Index: 196247 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.7378. Min Act: -0.1700
Data Index: 5302315 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.7378. Min Act: -0.1700
Data Index: 4307344 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.7378. Min Act: -0.1700
Data Index: 249884 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.7065. Min Act: -0.1700
Data Index: 7637667 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.7065. Min Act: -0.1700
Data Index: 7953847 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6440. Min Act: -0.1700
Data Index: 8547212 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6753. Min Act: -0.1700
Data Index: 7404919 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6440. Min Act: -0.1700
Data Index: 7746500 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6128. Min Act: -0.1700
Data Index: 795609 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.6128. Min Act: -0.1700
Data Index: 7629183 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.5815. Min Act: -0.1700
Data Index: 6105846 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.5815. Min Act: -0.1700
Data Index: 3549000 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.5503. Min Act: -0.1700
Data Index: 6238419 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.4878. Min Act: -0.1700
Data Index: 826146 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.4878. Min Act: -0.1700
Data Index: 5661958 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.4878. Min Act: -0.1700
Data Index: 118113 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8315. Min Range: -5.8315
Max Act: 5.4878. Min Act: -0.1700
Data Index: 857357 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19