Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1843 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0204. Min Range: -7.0204
Max Act: 7.0204. Min Act: -0.1700
Data Index: 5214720 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.8329. Min Act: -0.1700
Data Index: 1436407 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.6767. Min Act: -0.1700
Data Index: 8454256 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.6142. Min Act: -0.1700
Data Index: 2223470 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.5829. Min Act: -0.1700
Data Index: 4840937 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.5829. Min Act: -0.1700
Data Index: 7570546 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.5829. Min Act: -0.1700
Data Index: 3056348 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.5517. Min Act: -0.1700
Data Index: 1206336 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.5517. Min Act: -0.1700
Data Index: 7812133 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.5204. Min Act: -0.1700
Data Index: 808122 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.5204. Min Act: -0.1700
Data Index: 882464 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.4892. Min Act: -0.1700
Data Index: 388101 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.4892. Min Act: -0.1700
Data Index: 7276502 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.4579. Min Act: -0.1700
Data Index: 7367619 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.4267. Min Act: -0.1700
Data Index: 1220587 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.4267. Min Act: -0.1700
Data Index: 7701345 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.4267. Min Act: -0.1700
Data Index: 2843570 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.3642. Min Act: -0.1700
Data Index: 6931709 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.3954. Min Act: -0.1700
Data Index: 7823370 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0204. Min Range: -7.0204
Max Act: 6.3642. Min Act: -0.1700
Data Index: 2685265 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19