Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 871 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1440. Min Range: -3.1440
Max Act: 3.1440. Min Act: -0.1700
Data Index: 4241813 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1440. Min Range: -3.1440
Max Act: 3.0336. Min Act: -0.1700
Data Index: 4562148 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.9388. Min Act: -0.1700
Data Index: 2240954 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.9229. Min Act: -0.1700
Data Index: 1790655 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.9546. Min Act: -0.1700
Data Index: 394964 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.9388. Min Act: -0.1700
Data Index: 1354629 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.9071. Min Act: -0.1700
Data Index: 7024493 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8912. Min Act: -0.1700
Data Index: 6802531 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.9071. Min Act: -0.1700
Data Index: 2941835 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8912. Min Act: -0.1700
Data Index: 6965224 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.9071. Min Act: -0.1700
Data Index: 7296989 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8912. Min Act: -0.1700
Data Index: 2522580 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8753. Min Act: -0.1700
Data Index: 6207040 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8436. Min Act: -0.1700
Data Index: 5121352 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8436. Min Act: -0.1700
Data Index: 4080989 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8277. Min Act: -0.1700
Data Index: 3304081 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8753. Min Act: -0.1700
Data Index: 114345 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8118. Min Act: -0.1700
Data Index: 3412901 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8436. Min Act: -0.1700
Data Index: 207359 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1440. Min Range: -3.1440
Max Act: 2.8277. Min Act: -0.1700
Data Index: 1630792 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19