Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3937 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.9302. Min Act: -0.1700
Data Index: 6216685 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.8677. Min Act: -0.1700
Data Index: 8491256 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.8677. Min Act: -0.1700
Data Index: 3568574 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.8052. Min Act: -0.1700
Data Index: 3038897 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.7739. Min Act: -0.1700
Data Index: 1126902 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.7427. Min Act: -0.1700
Data Index: 4787642 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6489. Min Act: -0.1700
Data Index: 4394702 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6802. Min Act: -0.1700
Data Index: 7526832 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6489. Min Act: -0.1700
Data Index: 1424813 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6489. Min Act: -0.1700
Data Index: 3564344 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6802. Min Act: -0.1700
Data Index: 5250768 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6489. Min Act: -0.1700
Data Index: 4794237 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6489. Min Act: -0.1700
Data Index: 2854622 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6802. Min Act: -0.1700
Data Index: 7072805 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6489. Min Act: -0.1700
Data Index: 4580620 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6177. Min Act: -0.1700
Data Index: 6030203 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6177. Min Act: -0.1700
Data Index: 6451852 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6177. Min Act: -0.1700
Data Index: 7220807 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6489. Min Act: -0.1700
Data Index: 1790926 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9302. Min Range: -5.9302
Max Act: 5.6177. Min Act: -0.1700
Data Index: 5426843 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19