Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1696. Min Range: -8.1696
Max Act: 8.1696. Min Act: -0.1700
Data Index: 4526133 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1696. Min Range: -8.1696
Max Act: 8.1071. Min Act: -0.1700
Data Index: 6637784 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.9196. Min Act: -0.1700
Data Index: 1453112 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.9196. Min Act: -0.1700
Data Index: 3514327 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.7946. Min Act: -0.1700
Data Index: 3860282 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.7946. Min Act: -0.1700
Data Index: 3583824 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.7946. Min Act: -0.1699
Data Index: 6004985 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.7946. Min Act: -0.1700
Data Index: 5578312 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.6071. Min Act: -0.1700
Data Index: 387677 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5446. Min Act: -0.1700
Data Index: 353074 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.6071. Min Act: -0.1700
Data Index: 4307895 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5446. Min Act: -0.1700
Data Index: 4476586 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.6071. Min Act: -0.1700
Data Index: 814517 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5446. Min Act: -0.1700
Data Index: 178693 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5446. Min Act: -0.1700
Data Index: 6763419 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5446. Min Act: -0.1700
Data Index: 3493539 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5446. Min Act: -0.1700
Data Index: 3254028 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5446. Min Act: -0.1700
Data Index: 8616198 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5133. Min Act: -0.1700
Data Index: 7130859 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1696. Min Range: -8.1696
Max Act: 7.5133. Min Act: -0.1700
Data Index: 6480252 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19