Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.3543. Min Act: -0.1700
Data Index: 1400259 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.3230. Min Act: -0.1700
Data Index: 2643171 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.3230. Min Act: -0.1700
Data Index: 1338795 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.2918. Min Act: -0.1700
Data Index: 8142046 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.2293. Min Act: -0.1700
Data Index: 1737703 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.2605. Min Act: -0.1700
Data Index: 193395 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1980. Min Act: -0.1700
Data Index: 8052482 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1980. Min Act: -0.1700
Data Index: 8420796 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1980. Min Act: -0.1700
Data Index: 3315405 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1980. Min Act: -0.1700
Data Index: 8035236 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1668. Min Act: -0.1699
Data Index: 4448938 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1668. Min Act: -0.1700
Data Index: 8166097 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1355. Min Act: -0.1700
Data Index: 8284548 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1355. Min Act: -0.1700
Data Index: 2314565 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1355. Min Act: -0.1700
Data Index: 3006291 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1043. Min Act: -0.1700
Data Index: 7868714 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1043. Min Act: -0.1700
Data Index: 778117 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.0730. Min Act: -0.1700
Data Index: 1398729 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1043. Min Act: -0.1700
Data Index: 2011816 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3543. Min Range: -5.3543
Max Act: 5.1043. Min Act: -0.1700
Data Index: 635279 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19