Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.3397. Min Act: -0.1700
Data Index: 7912886 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.2772. Min Act: -0.1700
Data Index: 1160703 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.2460. Min Act: -0.1700
Data Index: 4052945 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.2460. Min Act: -0.1700
Data Index: 1939497 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.1210. Min Act: -0.1700
Data Index: 5629573 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.0897. Min Act: -0.1700
Data Index: 2196758 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.0585. Min Act: -0.1700
Data Index: 4877900 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.1210. Min Act: -0.1700
Data Index: 1610503 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.0272. Min Act: -0.1700
Data Index: 4897291 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.0897. Min Act: -0.1700
Data Index: 3029405 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.0272. Min Act: -0.1700
Data Index: 288696 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3397. Min Range: -8.3397
Max Act: 8.0272. Min Act: -0.1700
Data Index: 550299 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3397. Min Range: -8.3397
Max Act: 7.9960. Min Act: -0.1700
Data Index: 108871 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3397. Min Range: -8.3397
Max Act: 7.9647. Min Act: -0.1700
Data Index: 6743694 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3397. Min Range: -8.3397
Max Act: 7.9960. Min Act: -0.1700
Data Index: 4410529 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3397. Min Range: -8.3397
Max Act: 7.9335. Min Act: -0.1700
Data Index: 1174746 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3397. Min Range: -8.3397
Max Act: 7.9335. Min Act: -0.1700
Data Index: 7005258 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3397. Min Range: -8.3397
Max Act: 7.9022. Min Act: -0.1700
Data Index: 7313916 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3397. Min Range: -8.3397
Max Act: 7.9335. Min Act: -0.1700
Data Index: 8778796 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3397. Min Range: -8.3397
Max Act: 7.9335. Min Act: -0.1700
Data Index: 4645374 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19