Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5255 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.4482. Min Act: -0.1700
Data Index: 5112255 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.3425. Min Act: -0.1700
Data Index: 1224074 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.3425. Min Act: -0.1699
Data Index: 8359703 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.3425. Min Act: -0.1695
Data Index: 5109347 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.3248. Min Act: -0.1700
Data Index: 4117317 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.3072. Min Act: -0.1699
Data Index: 7922076 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.3072. Min Act: -0.1700
Data Index: 915831 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.3248. Min Act: -0.1698
Data Index: 4621313 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.3072. Min Act: -0.1700
Data Index: 8043324 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2896. Min Act: -0.1700
Data Index: 3226378 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2543. Min Act: -0.1700
Data Index: 2816562 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2719. Min Act: -0.1699
Data Index: 1338412 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2719. Min Act: -0.1700
Data Index: 7561630 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2543. Min Act: -0.1700
Data Index: 2328843 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2366. Min Act: -0.1700
Data Index: 7539941 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2543. Min Act: -0.1699
Data Index: 5478423 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2543. Min Act: -0.1700
Data Index: 2687922 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2190. Min Act: -0.1699
Data Index: 5452544 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2366. Min Act: -0.1700
Data Index: 4636179 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4482. Min Range: -1.4482
Max Act: 1.2543. Min Act: -0.1697
Data Index: 197251 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19