Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1516 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.3224. Min Act: -0.1700
Data Index: 5278377 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.3536. Min Act: -0.1700
Data Index: 3528212 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.2911. Min Act: -0.1700
Data Index: 1444886 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.1974. Min Act: -0.1700
Data Index: 298566 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.1036. Min Act: -0.1700
Data Index: 8290068 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.1349. Min Act: -0.1700
Data Index: 2067749 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.0411. Min Act: -0.1700
Data Index: 2604728 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.0411. Min Act: -0.1700
Data Index: 6299218 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.0411. Min Act: -0.1700
Data Index: 1646082 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.0099. Min Act: -0.1700
Data Index: 4282561 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.0099. Min Act: -0.1700
Data Index: 637134 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3536. Min Range: -6.3536
Max Act: 6.0099. Min Act: -0.1700
Data Index: 6327024 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3536. Min Range: -6.3536
Max Act: 5.9786. Min Act: -0.1700
Data Index: 552697 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3536. Min Range: -6.3536
Max Act: 5.9161. Min Act: -0.1700
Data Index: 1304884 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3536. Min Range: -6.3536
Max Act: 5.9474. Min Act: -0.1700
Data Index: 4952387 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3536. Min Range: -6.3536
Max Act: 5.9474. Min Act: -0.1700
Data Index: 5593317 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3536. Min Range: -6.3536
Max Act: 5.9161. Min Act: -0.1700
Data Index: 1610500 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3536. Min Range: -6.3536
Max Act: 5.9161. Min Act: -0.1700
Data Index: 2000975 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3536. Min Range: -6.3536
Max Act: 5.8849. Min Act: -0.1700
Data Index: 1964124 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3536. Min Range: -6.3536
Max Act: 5.8849. Min Act: -0.1700
Data Index: 6868849 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19