Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1236. Min Range: -5.1236
Max Act: 5.1236. Min Act: -0.1700
Data Index: 6913470 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.9986. Min Act: -0.1700
Data Index: 5705767 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.9986. Min Act: -0.1700
Data Index: 3014240 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.9361. Min Act: -0.1700
Data Index: 5387111 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.9048. Min Act: -0.1700
Data Index: 7653479 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.9048. Min Act: -0.1700
Data Index: 4424033 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.9048. Min Act: -0.1700
Data Index: 2330285 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.8736. Min Act: -0.1700
Data Index: 7254638 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.8736. Min Act: -0.1700
Data Index: 3278145 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.8423. Min Act: -0.1700
Data Index: 1810373 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.8423. Min Act: -0.1700
Data Index: 5697463 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.8423. Min Act: -0.1700
Data Index: 2317062 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.8111. Min Act: -0.1700
Data Index: 6156522 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.7798. Min Act: -0.1700
Data Index: 3380797 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.7486. Min Act: -0.1700
Data Index: 3158042 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.7798. Min Act: -0.1700
Data Index: 4588172 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.7798. Min Act: -0.1700
Data Index: 1148733 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.7798. Min Act: -0.1700
Data Index: 3122641 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.7798. Min Act: -0.1700
Data Index: 2085168 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1236. Min Range: -5.1236
Max Act: 4.7486. Min Act: -0.1700
Data Index: 2000130 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19