Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5496 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.4207. Min Act: -0.1700
Data Index: 2275190 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.4044. Min Act: -0.1699
Data Index: 6634556 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.4044. Min Act: -0.1700
Data Index: 4067894 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.4044. Min Act: -0.1700
Data Index: 6778389 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3881. Min Act: -0.1700
Data Index: 1840711 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3881. Min Act: -0.1700
Data Index: 8532964 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3717. Min Act: -0.1700
Data Index: 1465487 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3554. Min Act: -0.1700
Data Index: 2302520 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3226. Min Act: -0.1700
Data Index: 4366248 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3226. Min Act: -0.1700
Data Index: 3765624 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3061. Min Act: -0.1700
Data Index: 3836614 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.2897. Min Act: -0.1700
Data Index: 4930684 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3061. Min Act: -0.1700
Data Index: 1717944 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.2897. Min Act: -0.1700
Data Index: 4966523 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.2897. Min Act: -0.1700
Data Index: 8781929 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.2897. Min Act: -0.1700
Data Index: 2189195 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.2897. Min Act: -0.1700
Data Index: 1355192 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.2897. Min Act: -0.1700
Data Index: 7959941 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.3061. Min Act: -0.1700
Data Index: 2742525 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4207. Min Range: -2.4207
Max Act: 2.2897. Min Act: -0.1700
Data Index: 1768634 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19