Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.6679. Min Act: -0.1700
Data Index: 3114367 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.6367. Min Act: -0.1700
Data Index: 7508929 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.5429. Min Act: -0.1700
Data Index: 8045405 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.5429. Min Act: -0.1700
Data Index: 8820840 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.4804. Min Act: -0.1700
Data Index: 6405167 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.3554. Min Act: -0.1700
Data Index: 5076024 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.2617. Min Act: -0.1700
Data Index: 4983041 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1992. Min Act: -0.1700
Data Index: 1623576 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.2304. Min Act: -0.1700
Data Index: 3478551 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1992. Min Act: -0.1700
Data Index: 2371511 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1992. Min Act: -0.1700
Data Index: 3166287 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.2304. Min Act: -0.1700
Data Index: 4560740 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1679. Min Act: -0.1700
Data Index: 6005110 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1679. Min Act: -0.1700
Data Index: 6925821 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1367. Min Act: -0.1700
Data Index: 6175826 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1367. Min Act: -0.1700
Data Index: 2643164 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1367. Min Act: -0.1700
Data Index: 4868643 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1054. Min Act: -0.1700
Data Index: 6865668 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1054. Min Act: -0.1700
Data Index: 2601784 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6679. Min Range: -6.6679
Max Act: 6.1054. Min Act: -0.1700
Data Index: 5992969 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19