Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.8251. Min Act: -0.1700
Data Index: 729596 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.7314. Min Act: -0.1700
Data Index: 536113 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.7626. Min Act: -0.1700
Data Index: 6840415 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.5751. Min Act: -0.1700
Data Index: 3233014 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.5126. Min Act: -0.1700
Data Index: 3435295 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.4814. Min Act: -0.1700
Data Index: 4600831 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.5126. Min Act: -0.1700
Data Index: 6698245 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.3251. Min Act: -0.1700
Data Index: 3966828 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.3876. Min Act: -0.1700
Data Index: 193492 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.3564. Min Act: -0.1700
Data Index: 8404010 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.2314. Min Act: -0.1700
Data Index: 2282907 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.2314. Min Act: -0.1700
Data Index: 2102615 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.2626. Min Act: -0.1700
Data Index: 3217395 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.2314. Min Act: -0.1700
Data Index: 7222118 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.2314. Min Act: -0.1700
Data Index: 6758240 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.2001. Min Act: -0.1700
Data Index: 8020092 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.2001. Min Act: -0.1700
Data Index: 6060272 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.1689. Min Act: -0.1700
Data Index: 1498143 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.1376. Min Act: -0.1700
Data Index: 6199046 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8251. Min Range: -7.8251
Max Act: 7.1689. Min Act: -0.1700
Data Index: 4587928 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19