Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0287. Min Range: -5.0287
Max Act: 5.0287. Min Act: -0.1700
Data Index: 4525189 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.9350. Min Act: -0.1700
Data Index: 1609322 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.9037. Min Act: -0.1700
Data Index: 6644729 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8725. Min Act: -0.1700
Data Index: 4182909 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8725. Min Act: -0.1700
Data Index: 7724388 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8725. Min Act: -0.1700
Data Index: 7136658 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.9037. Min Act: -0.1700
Data Index: 7821260 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8412. Min Act: -0.1700
Data Index: 125969 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8100. Min Act: -0.1700
Data Index: 4843860 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8100. Min Act: -0.1700
Data Index: 3190996 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8412. Min Act: -0.1700
Data Index: 8480683 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8100. Min Act: -0.1700
Data Index: 8138321 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8100. Min Act: -0.1700
Data Index: 7315846 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8100. Min Act: -0.1700
Data Index: 5056799 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.7787. Min Act: -0.1700
Data Index: 1724458 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.8100. Min Act: -0.1700
Data Index: 5811567 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.7787. Min Act: -0.1700
Data Index: 8419690 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.7475. Min Act: -0.1700
Data Index: 8410395 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.7475. Min Act: -0.1700
Data Index: 2889957 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0287. Min Range: -5.0287
Max Act: 4.7475. Min Act: -0.1700
Data Index: 3967794 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19