Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2401 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2483. Min Range: -10.2483
Max Act: 10.2483. Min Act: -0.1700
Data Index: 7811587 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2483. Min Range: -10.2483
Max Act: 10.0608. Min Act: -0.1700
Data Index: 8322728 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.9358. Min Act: -0.1700
Data Index: 2001950 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.9358. Min Act: -0.1700
Data Index: 7042228 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.8733. Min Act: -0.1700
Data Index: 8804726 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.8108. Min Act: -0.1700
Data Index: 2570529 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.8108. Min Act: -0.1700
Data Index: 4272823 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.8108. Min Act: -0.1700
Data Index: 3729007 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.6233. Min Act: -0.1700
Data Index: 6702920 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.6233. Min Act: -0.1700
Data Index: 2426342 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.6233. Min Act: -0.1700
Data Index: 7788058 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.6233. Min Act: -0.1700
Data Index: 2908678 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.5608. Min Act: -0.1700
Data Index: 6733228 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.4983. Min Act: -0.1700
Data Index: 7854778 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.4983. Min Act: -0.1700
Data Index: 4133753 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.4358. Min Act: -0.1700
Data Index: 4393571 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.3733. Min Act: -0.1700
Data Index: 1067109 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.3733. Min Act: -0.1700
Data Index: 2024848 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.3108. Min Act: -0.1700
Data Index: 1704958 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2483. Min Range: -10.2483
Max Act: 9.3108. Min Act: -0.1700
Data Index: 2620877 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19