Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.5400. Min Act: -0.1700
Data Index: 8467113 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.5400. Min Act: -0.1700
Data Index: 2478602 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.4775. Min Act: -0.1700
Data Index: 8807581 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.4775. Min Act: -0.1700
Data Index: 4579194 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.4150. Min Act: -0.1700
Data Index: 6464357 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.3525. Min Act: -0.1700
Data Index: 6811849 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.4150. Min Act: -0.1700
Data Index: 574133 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.4150. Min Act: -0.1700
Data Index: 5538447 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.3525. Min Act: -0.1700
Data Index: 7412745 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.3525. Min Act: -0.1700
Data Index: 5140592 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2900. Min Act: -0.1700
Data Index: 1766670 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2900. Min Act: -0.1300
Data Index: 574142 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2900. Min Act: -0.1700
Data Index: 6913423 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2900. Min Act: -0.1700
Data Index: 1885349 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2900. Min Act: -0.1700
Data Index: 709404 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2900. Min Act: -0.1700
Data Index: 928486 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2900. Min Act: -0.1686
Data Index: 5528410 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2275. Min Act: -0.1699
Data Index: 4829203 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2275. Min Act: -0.1700
Data Index: 2772201 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5400. Min Range: -8.5400
Max Act: 8.2275. Min Act: -0.1700
Data Index: 942574 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19