Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1647 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.7274. Min Act: -0.1700
Data Index: 5342991 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.5399. Min Act: -0.1700
Data Index: 695209 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.5086. Min Act: -0.1700
Data Index: 7581421 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.4774. Min Act: -0.1700
Data Index: 6585961 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.4461. Min Act: -0.1700
Data Index: 8538480 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.4149. Min Act: -0.1700
Data Index: 2470684 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.4149. Min Act: -0.1700
Data Index: 652911 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.3836. Min Act: -0.1700
Data Index: 4861803 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.3836. Min Act: -0.1700
Data Index: 1867257 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.3836. Min Act: -0.1700
Data Index: 3430259 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.3524. Min Act: -0.1700
Data Index: 2366371 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.3211. Min Act: -0.1700
Data Index: 7054441 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.3211. Min Act: -0.1700
Data Index: 1230686 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.3211. Min Act: -0.1700
Data Index: 4474003 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.3211. Min Act: -0.1700
Data Index: 4165829 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.2586. Min Act: -0.1700
Data Index: 1768445 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.2899. Min Act: -0.1700
Data Index: 8824469 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.2586. Min Act: -0.1700
Data Index: 7123928 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.2586. Min Act: -0.1700
Data Index: 2729849 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7274. Min Range: -6.7274
Max Act: 6.2274. Min Act: -0.1700
Data Index: 3600274 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19