Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 630 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.4324. Min Act: -0.1700
Data Index: 6272902 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.2137. Min Act: -0.1700
Data Index: 7036309 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1512. Min Act: -0.1700
Data Index: 1651072 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.2137. Min Act: -0.1700
Data Index: 288823 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1512. Min Act: -0.1700
Data Index: 7669062 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1824. Min Act: -0.1700
Data Index: 1271024 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1512. Min Act: -0.1700
Data Index: 5083868 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0574. Min Act: -0.1700
Data Index: 3370652 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0574. Min Act: -0.1700
Data Index: 2014401 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0262. Min Act: -0.1700
Data Index: 7306206 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9949. Min Act: -0.1700
Data Index: 8514195 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9949. Min Act: -0.1700
Data Index: 5256065 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9949. Min Act: -0.1700
Data Index: 7245661 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9637. Min Act: -0.1700
Data Index: 4261651 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9637. Min Act: -0.1700
Data Index: 7947843 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9012. Min Act: -0.1700
Data Index: 6930092 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9324. Min Act: -0.1700
Data Index: 4681832 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9324. Min Act: -0.1700
Data Index: 2535572 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9324. Min Act: -0.1700
Data Index: 7068693 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4324. Min Range: -5.4324
Max Act: 4.9012. Min Act: -0.1700
Data Index: 3800551 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19