Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3139 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1979. Min Range: -6.1979
Max Act: 6.1979. Min Act: -0.1700
Data Index: 6423199 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1979. Min Range: -6.1979
Max Act: 6.0416. Min Act: -0.1700
Data Index: 413089 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1979. Min Range: -6.1979
Max Act: 6.0104. Min Act: -0.1700
Data Index: 620178 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.9791. Min Act: -0.1700
Data Index: 620177 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.9479. Min Act: -0.1700
Data Index: 5512605 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.9479. Min Act: -0.1700
Data Index: 2083053 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.9166. Min Act: -0.1700
Data Index: 6319338 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.9166. Min Act: -0.1700
Data Index: 6423206 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.8854. Min Act: -0.1700
Data Index: 5936456 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.8854. Min Act: -0.1700
Data Index: 7816145 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.8541. Min Act: -0.1700
Data Index: 7366575 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.7916. Min Act: -0.1700
Data Index: 7816147 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.8541. Min Act: -0.1700
Data Index: 3719031 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.7604. Min Act: -0.1700
Data Index: 6632625 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.7916. Min Act: -0.1700
Data Index: 110196 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.7916. Min Act: -0.1700
Data Index: 2424218 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.7916. Min Act: -0.1700
Data Index: 1541514 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.7916. Min Act: -0.1700
Data Index: 8490439 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.7291. Min Act: -0.1700
Data Index: 3647338 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1979. Min Range: -6.1979
Max Act: 5.7916. Min Act: -0.1700
Data Index: 6226759 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19