Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1979. Min Range: -5.1979
Max Act: 5.1979. Min Act: -0.1700
Data Index: 3379535 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1979. Min Range: -5.1979
Max Act: 5.1354. Min Act: -0.1700
Data Index: 1707085 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1979. Min Range: -5.1979
Max Act: 5.0729. Min Act: -0.1700
Data Index: 8461405 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.9479. Min Act: -0.1700
Data Index: 6012734 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.9479. Min Act: -0.1700
Data Index: 6734832 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.9791. Min Act: -0.1700
Data Index: 3529617 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.9166. Min Act: -0.1700
Data Index: 3817086 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.9479. Min Act: -0.1700
Data Index: 1253890 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8854. Min Act: -0.1700
Data Index: 8789402 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8854. Min Act: -0.1700
Data Index: 2264545 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8854. Min Act: -0.1700
Data Index: 6501171 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8854. Min Act: -0.1700
Data Index: 3181452 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8541. Min Act: -0.1700
Data Index: 5671363 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8541. Min Act: -0.1700
Data Index: 699826 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8541. Min Act: -0.1700
Data Index: 7860119 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8541. Min Act: -0.1700
Data Index: 2416467 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8541. Min Act: -0.1700
Data Index: 7721796 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.8229. Min Act: -0.1700
Data Index: 909998 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.7604. Min Act: -0.1700
Data Index: 6906924 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1979. Min Range: -5.1979
Max Act: 4.7916. Min Act: -0.1700
Data Index: 1654595 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19