Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.6768. Min Act: -0.1700
Data Index: 6992334 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.6142. Min Act: -0.1700
Data Index: 8782039 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.6298. Min Act: -0.1700
Data Index: 1908072 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5985. Min Act: -0.1700
Data Index: 5314920 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5672. Min Act: -0.1700
Data Index: 6763068 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5985. Min Act: -0.1700
Data Index: 5827386 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5516. Min Act: -0.1700
Data Index: 3930934 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5203. Min Act: -0.1700
Data Index: 8104742 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5359. Min Act: -0.1700
Data Index: 3201202 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5359. Min Act: -0.1700
Data Index: 6520997 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5516. Min Act: -0.1700
Data Index: 6189006 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5203. Min Act: -0.1700
Data Index: 3448054 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5203. Min Act: -0.1700
Data Index: 882815 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5046. Min Act: -0.1700
Data Index: 5287095 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.5046. Min Act: -0.1700
Data Index: 6300347 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.4889. Min Act: -0.1700
Data Index: 8774808 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.4576. Min Act: -0.1700
Data Index: 7394738 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.4889. Min Act: -0.1700
Data Index: 7185324 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.4733. Min Act: -0.1700
Data Index: 8697930 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6768. Min Range: -3.6768
Max Act: 3.4889. Min Act: -0.1700
Data Index: 7223268 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19