Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.5695. Min Act: -0.1700
Data Index: 4816701 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.5382. Min Act: -0.1700
Data Index: 8730009 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4757. Min Act: -0.1700
Data Index: 1005321 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4445. Min Act: -0.1700
Data Index: 4848306 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.5070. Min Act: -0.1700
Data Index: 1892031 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4445. Min Act: -0.1700
Data Index: 1580698 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4132. Min Act: -0.1700
Data Index: 2007833 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4445. Min Act: -0.1700
Data Index: 8817816 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4445. Min Act: -0.1700
Data Index: 7967512 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4132. Min Act: -0.1700
Data Index: 5059674 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4445. Min Act: -0.1700
Data Index: 6376484 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4132. Min Act: -0.1700
Data Index: 394195 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.3507. Min Act: -0.1700
Data Index: 4906663 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4132. Min Act: -0.1700
Data Index: 4399523 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.3820. Min Act: -0.1700
Data Index: 3991897 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.3820. Min Act: -0.1700
Data Index: 7687077 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.3820. Min Act: -0.1700
Data Index: 2140151 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.3507. Min Act: -0.1700
Data Index: 6684097 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.3820. Min Act: -0.1700
Data Index: 4157993 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5695. Min Range: -4.5695
Max Act: 4.4132. Min Act: -0.1700
Data Index: 4836008 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19