Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.6199. Min Act: -0.1700
Data Index: 5049267 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.5261. Min Act: -0.1700
Data Index: 7145510 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.4011. Min Act: -0.1700
Data Index: 5147115 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.3074. Min Act: -0.1700
Data Index: 8693633 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.2761. Min Act: -0.1700
Data Index: 844913 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.1824. Min Act: -0.1700
Data Index: 7691744 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.1199. Min Act: -0.1700
Data Index: 4490039 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.1511. Min Act: -0.1700
Data Index: 7381571 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.1511. Min Act: -0.1700
Data Index: 644667 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.1199. Min Act: -0.1700
Data Index: 406147 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.1199. Min Act: -0.1700
Data Index: 4241440 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.0886. Min Act: -0.1700
Data Index: 526056 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.1199. Min Act: -0.1700
Data Index: 7796016 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.0886. Min Act: -0.1700
Data Index: 6894050 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.0574. Min Act: -0.1700
Data Index: 5506395 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6199. Min Range: -5.6199
Max Act: 5.0261. Min Act: -0.1700
Data Index: 6659065 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6199. Min Range: -5.6199
Max Act: 4.9949. Min Act: -0.1700
Data Index: 5969953 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6199. Min Range: -5.6199
Max Act: 4.9949. Min Act: -0.1700
Data Index: 6272368 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6199. Min Range: -5.6199
Max Act: 4.9636. Min Act: -0.1700
Data Index: 3915836 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6199. Min Range: -5.6199
Max Act: 4.9324. Min Act: -0.1700
Data Index: 3170475 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19