Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2769 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.3409. Min Act: -0.1700
Data Index: 1829254 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.2159. Min Act: -0.1700
Data Index: 6855794 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.1534. Min Act: -0.1700
Data Index: 2137785 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.1534. Min Act: -0.1700
Data Index: 1242580 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.1221. Min Act: -0.1700
Data Index: 3107633 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.1221. Min Act: -0.1700
Data Index: 5417622 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0909. Min Act: -0.1700
Data Index: 4664602 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0909. Min Act: -0.1700
Data Index: 8089803 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0909. Min Act: -0.1700
Data Index: 4828692 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0596. Min Act: -0.1700
Data Index: 3075517 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0596. Min Act: -0.1700
Data Index: 1522993 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0596. Min Act: -0.1700
Data Index: 2939928 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0596. Min Act: -0.1700
Data Index: 881608 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0596. Min Act: -0.1700
Data Index: 8384491 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0596. Min Act: -0.1700
Data Index: 648119 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0284. Min Act: -0.1700
Data Index: 1829256 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0284. Min Act: -0.1700
Data Index: 4493410 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3409. Min Range: -5.3409
Max Act: 4.9971. Min Act: -0.1700
Data Index: 5617500 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3409. Min Range: -5.3409
Max Act: 5.0284. Min Act: -0.1700
Data Index: 648117 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3409. Min Range: -5.3409
Max Act: 4.9659. Min Act: -0.1700
Data Index: 5684427 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19