Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2271. Min Range: -5.2271
Max Act: 5.2271. Min Act: -0.1700
Data Index: 7139383 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2271. Min Range: -5.2271
Max Act: 5.1646. Min Act: -0.1700
Data Index: 7391147 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2271. Min Range: -5.2271
Max Act: 5.1334. Min Act: -0.1700
Data Index: 280102 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2271. Min Range: -5.2271
Max Act: 5.0396. Min Act: -0.1700
Data Index: 1574770 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2271. Min Range: -5.2271
Max Act: 5.0084. Min Act: -0.1700
Data Index: 589715 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2271. Min Range: -5.2271
Max Act: 5.0084. Min Act: -0.1700
Data Index: 560892 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.9459. Min Act: -0.1700
Data Index: 5461775 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.9146. Min Act: -0.1700
Data Index: 1709803 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.9459. Min Act: -0.1700
Data Index: 396980 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.9459. Min Act: -0.1700
Data Index: 7125978 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.9146. Min Act: -0.1700
Data Index: 3090285 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.8521. Min Act: -0.1700
Data Index: 501400 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.8521. Min Act: -0.1700
Data Index: 6329728 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.8521. Min Act: -0.1700
Data Index: 5069485 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.8834. Min Act: -0.1700
Data Index: 1053449 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.8209. Min Act: -0.1700
Data Index: 3053559 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.8521. Min Act: -0.1700
Data Index: 8435117 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.8521. Min Act: -0.1700
Data Index: 5252120 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.7896. Min Act: -0.1700
Data Index: 4757994 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2271. Min Range: -5.2271
Max Act: 4.7271. Min Act: -0.1700
Data Index: 7356243 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19