Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0305. Min Range: -6.0305
Max Act: 6.0305. Min Act: -0.1700
Data Index: 1540580 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.9055. Min Act: -0.1700
Data Index: 1670671 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.9055. Min Act: -0.1700
Data Index: 4212096 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.9055. Min Act: -0.1700
Data Index: 5762444 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.8743. Min Act: -0.1700
Data Index: 6306781 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.8118. Min Act: -0.1700
Data Index: 795311 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.8118. Min Act: -0.1700
Data Index: 4868190 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.8430. Min Act: -0.1700
Data Index: 601089 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.8430. Min Act: -0.1700
Data Index: 459056 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7805. Min Act: -0.1700
Data Index: 1557737 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.8118. Min Act: -0.1700
Data Index: 5570831 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7805. Min Act: -0.1700
Data Index: 8816254 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7493. Min Act: -0.1700
Data Index: 4409245 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7493. Min Act: -0.1700
Data Index: 5059466 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7180. Min Act: -0.1700
Data Index: 7760139 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7493. Min Act: -0.1700
Data Index: 7622787 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7180. Min Act: -0.1700
Data Index: 5582234 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4876241 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2366399 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0305. Min Range: -6.0305
Max Act: 5.6555. Min Act: -0.1700
Data Index: 1471729 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19