Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2032 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.6467. Min Act: -0.1700
Data Index: 1318439 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.3342. Min Act: -0.1700
Data Index: 1742758 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.3967. Min Act: -0.1700
Data Index: 324571 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.2717. Min Act: -0.1700
Data Index: 2478909 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.1467. Min Act: -0.1700
Data Index: 2537768 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.1467. Min Act: -0.1700
Data Index: 5434435 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.0842. Min Act: -0.1700
Data Index: 2964880 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.0842. Min Act: -0.1700
Data Index: 4514908 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.0217. Min Act: -0.1700
Data Index: 6380392 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6467. Min Range: -9.6467
Max Act: 9.0217. Min Act: -0.1700
Data Index: 7383526 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.9592. Min Act: -0.1700
Data Index: 6247328 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.9592. Min Act: -0.1700
Data Index: 5443204 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.9592. Min Act: -0.1700
Data Index: 2265633 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.9592. Min Act: -0.1700
Data Index: 4676114 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.9592. Min Act: -0.1700
Data Index: 3167600 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.8967. Min Act: -0.1700
Data Index: 5276712 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.8342. Min Act: -0.1700
Data Index: 2081759 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.8967. Min Act: -0.1700
Data Index: 3355382 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.8342. Min Act: -0.1700
Data Index: 7057458 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6467. Min Range: -9.6467
Max Act: 8.8967. Min Act: -0.1700
Data Index: 5366366 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19