Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2876 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1315. Min Range: -8.1315
Max Act: 8.1315. Min Act: -0.1700
Data Index: 4298845 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.6940. Min Act: -0.1700
Data Index: 4987639 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.4440. Min Act: -0.1700
Data Index: 115763 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.3815. Min Act: -0.1700
Data Index: 1458354 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.4128. Min Act: -0.1700
Data Index: 6846258 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.3815. Min Act: -0.1700
Data Index: 404465 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.3190. Min Act: -0.1700
Data Index: 255583 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.2878. Min Act: -0.1700
Data Index: 1843862 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.3190. Min Act: -0.1700
Data Index: 8137358 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.2878. Min Act: -0.1700
Data Index: 2340046 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.1628. Min Act: -0.1700
Data Index: 1458356 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.1940. Min Act: -0.1700
Data Index: 8054423 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.1628. Min Act: -0.1700
Data Index: 2296697 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.1628. Min Act: -0.1700
Data Index: 2719071 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.1315. Min Act: -0.1700
Data Index: 115760 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.1003. Min Act: -0.1700
Data Index: 4274859 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.0690. Min Act: -0.1700
Data Index: 519208 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.0378. Min Act: -0.1700
Data Index: 8233981 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.0378. Min Act: -0.1700
Data Index: 2755211 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1315. Min Range: -8.1315
Max Act: 7.0378. Min Act: -0.1700
Data Index: 7160535 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19