Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.4203. Min Act: -0.1700
Data Index: 6700887 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.3266. Min Act: -0.1700
Data Index: 3438241 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.2328. Min Act: -0.1700
Data Index: 3823883 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.2641. Min Act: -0.1700
Data Index: 717234 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.2015. Min Act: -0.1700
Data Index: 155146 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.2015. Min Act: -0.1700
Data Index: 511574 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1703. Min Act: -0.1700
Data Index: 6455163 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.2015. Min Act: -0.1700
Data Index: 3906987 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.2015. Min Act: -0.1700
Data Index: 2180500 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1703. Min Act: -0.1700
Data Index: 5682503 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1703. Min Act: -0.1700
Data Index: 1188461 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1703. Min Act: -0.1700
Data Index: 3054060 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1390. Min Act: -0.1700
Data Index: 5711440 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1390. Min Act: -0.1700
Data Index: 4337535 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.2015. Min Act: -0.1700
Data Index: 72371 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1390. Min Act: -0.1700
Data Index: 1870530 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1703. Min Act: -0.1700
Data Index: 5033659 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1078. Min Act: -0.1700
Data Index: 717229 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1390. Min Act: -0.1700
Data Index: 1042796 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4203. Min Range: -4.4203
Max Act: 4.1078. Min Act: -0.1700
Data Index: 717228 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19