Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.5408. Min Act: -0.1700
Data Index: 646704 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4598. Min Act: -0.1678
Data Index: 2419039 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4598. Min Act: -0.1691
Data Index: 2542408 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4435. Min Act: -0.1695
Data Index: 5547768 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4435. Min Act: -0.1691
Data Index: 617206 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4272. Min Act: -0.1696
Data Index: 6319223 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4272. Min Act: -0.1700
Data Index: 8472010 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4272. Min Act: -0.1648
Data Index: 7315154 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4109. Min Act: -0.1700
Data Index: 1796502 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3946. Min Act: -0.1680
Data Index: 8131214 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.4109. Min Act: -0.1697
Data Index: 3690116 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3946. Min Act: -0.1699
Data Index: 432345 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3946. Min Act: -0.1697
Data Index: 7128191 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3946. Min Act: -0.1699
Data Index: 7076722 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3946. Min Act: -0.1700
Data Index: 4063332 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3783. Min Act: -0.1698
Data Index: 158011 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3783. Min Act: -0.1697
Data Index: 7128193 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3783. Min Act: -0.1700
Data Index: 8433133 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3783. Min Act: -0.1700
Data Index: 1889766 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5408. Min Range: -2.5408
Max Act: 2.3946. Min Act: -0.1700
Data Index: 1725721 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19