Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1723 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1765. Min Range: -6.1765
Max Act: 6.1765. Min Act: -0.1700
Data Index: 6240160 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1765. Min Range: -6.1765
Max Act: 6.1140. Min Act: -0.1700
Data Index: 1804431 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1765. Min Range: -6.1765
Max Act: 6.0515. Min Act: -0.1700
Data Index: 5199093 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.8953. Min Act: -0.1700
Data Index: 5971527 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.8953. Min Act: -0.1700
Data Index: 3366029 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.8640. Min Act: -0.1700
Data Index: 8636715 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.8640. Min Act: -0.1700
Data Index: 6450685 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.8328. Min Act: -0.1700
Data Index: 726194 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.7390. Min Act: -0.1700
Data Index: 4374384 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.7078. Min Act: -0.1700
Data Index: 2127729 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.7078. Min Act: -0.1700
Data Index: 4752606 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.6140. Min Act: -0.1700
Data Index: 2262037 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.6140. Min Act: -0.1700
Data Index: 7320408 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.5515. Min Act: -0.1700
Data Index: 1388253 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.5203. Min Act: -0.1700
Data Index: 7271099 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.4890. Min Act: -0.1700
Data Index: 2574330 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.4890. Min Act: -0.1700
Data Index: 3943603 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.4578. Min Act: -0.1700
Data Index: 2051574 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.3953. Min Act: -0.1700
Data Index: 7316209 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1765. Min Range: -6.1765
Max Act: 5.4578. Min Act: -0.1700
Data Index: 5139617 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19