Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3879 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.6373. Min Act: -0.1700
Data Index: 1486977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.5748. Min Act: -0.1700
Data Index: 4891969 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.4810. Min Act: -0.1700
Data Index: 1179896 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.4498. Min Act: -0.1700
Data Index: 710182 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.4498. Min Act: -0.1700
Data Index: 6868786 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.4185. Min Act: -0.1700
Data Index: 3523305 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.3873. Min Act: -0.1700
Data Index: 7658970 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.2935. Min Act: -0.1700
Data Index: 8092944 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.2935. Min Act: -0.1700
Data Index: 232747 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.2935. Min Act: -0.1700
Data Index: 2715241 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.2310. Min Act: -0.1700
Data Index: 7433184 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.2623. Min Act: -0.1700
Data Index: 2350168 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.1998. Min Act: -0.1700
Data Index: 5301793 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.1998. Min Act: -0.1700
Data Index: 4320615 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.1998. Min Act: -0.1700
Data Index: 4340347 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.1685. Min Act: -0.1700
Data Index: 3643315 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.1685. Min Act: -0.1700
Data Index: 5235036 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.1685. Min Act: -0.1700
Data Index: 7159835 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.1685. Min Act: -0.1700
Data Index: 2476709 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6373. Min Range: -6.6373
Max Act: 6.1373. Min Act: -0.1700
Data Index: 542293 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19