Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.2753. Min Act: -0.1700
Data Index: 6931350 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.1503. Min Act: -0.1700
Data Index: 6951770 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.1191. Min Act: -0.1700
Data Index: 1901825 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0878. Min Act: -0.1700
Data Index: 1501813 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 1641543 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0878. Min Act: -0.1700
Data Index: 8552119 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 6951771 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0253. Min Act: -0.1700
Data Index: 647059 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0253. Min Act: -0.1700
Data Index: 1419027 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0253. Min Act: -0.1700
Data Index: 4801435 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9941. Min Act: -0.1700
Data Index: 545472 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9628. Min Act: -0.1700
Data Index: 7526555 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9941. Min Act: -0.1700
Data Index: 545471 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9941. Min Act: -0.1700
Data Index: 5724353 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9628. Min Act: -0.1700
Data Index: 3257908 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9628. Min Act: -0.1700
Data Index: 4041274 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9316. Min Act: -0.1700
Data Index: 1871675 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9628. Min Act: -0.1700
Data Index: 404150 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9316. Min Act: -0.1700
Data Index: 3764193 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2753. Min Range: -5.2753
Max Act: 4.9316. Min Act: -0.1700
Data Index: 5523841 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19