Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2994 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.5605. Min Act: -0.1700
Data Index: 6402506 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.3730. Min Act: -0.1700
Data Index: 8187998 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.4042. Min Act: -0.1700
Data Index: 4579921 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.3105. Min Act: -0.1700
Data Index: 2332818 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.2480. Min Act: -0.1700
Data Index: 2451599 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.2480. Min Act: -0.1700
Data Index: 4769940 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.1855. Min Act: -0.1700
Data Index: 7398881 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.1855. Min Act: -0.1700
Data Index: 1111834 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.1542. Min Act: -0.1700
Data Index: 5131822 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.1230. Min Act: -0.1700
Data Index: 149434 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.1230. Min Act: -0.1700
Data Index: 5268157 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.0605. Min Act: -0.1700
Data Index: 7214413 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.0605. Min Act: -0.1700
Data Index: 7891067 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5605. Min Range: -7.5605
Max Act: 7.0292. Min Act: -0.1700
Data Index: 2326717 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5605. Min Range: -7.5605
Max Act: 6.9980. Min Act: -0.1700
Data Index: 7484493 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5605. Min Range: -7.5605
Max Act: 6.9980. Min Act: -0.1700
Data Index: 4684624 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5605. Min Range: -7.5605
Max Act: 6.9355. Min Act: -0.1700
Data Index: 4193059 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5605. Min Range: -7.5605
Max Act: 6.9355. Min Act: -0.1700
Data Index: 2135681 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5605. Min Range: -7.5605
Max Act: 6.9042. Min Act: -0.1700
Data Index: 4607437 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5605. Min Range: -7.5605
Max Act: 6.9042. Min Act: -0.1700
Data Index: 5796511 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19