Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1723 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.6870. Min Act: -0.1700
Data Index: 3075378 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.5932. Min Act: -0.1700
Data Index: 2511056 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.6557. Min Act: -0.1700
Data Index: 7079043 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.5620. Min Act: -0.1700
Data Index: 2289625 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.5620. Min Act: -0.1700
Data Index: 2211622 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.5307. Min Act: -0.1700
Data Index: 1451798 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.5307. Min Act: -0.1700
Data Index: 507472 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.5307. Min Act: -0.1700
Data Index: 4925902 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4995. Min Act: -0.1700
Data Index: 1243155 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4682. Min Act: -0.1700
Data Index: 928377 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4682. Min Act: -0.1700
Data Index: 2230685 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4370. Min Act: -0.1700
Data Index: 7699736 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4370. Min Act: -0.1700
Data Index: 8465062 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4370. Min Act: -0.1700
Data Index: 5766835 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.4370. Min Act: -0.1700
Data Index: 7832155 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.3745. Min Act: -0.1700
Data Index: 7560788 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.3745. Min Act: -0.1700
Data Index: 7759256 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7127277 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.3432. Min Act: -0.1700
Data Index: 990836 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6870. Min Range: -5.6870
Max Act: 5.3432. Min Act: -0.1700
Data Index: 6511387 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19