Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5275 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3453. Min Act: -0.1700
Data Index: 7778545 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2516. Min Act: -0.1700
Data Index: 5298914 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2516. Min Act: -0.1700
Data Index: 2916928 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2516. Min Act: -0.1700
Data Index: 3603823 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 6324035 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0328. Min Act: -0.1700
Data Index: 7299833 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0328. Min Act: -0.1700
Data Index: 5723125 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0016. Min Act: -0.1700
Data Index: 2992216 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0016. Min Act: -0.1700
Data Index: 5085360 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0016. Min Act: -0.1700
Data Index: 2617871 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0328. Min Act: -0.1700
Data Index: 6653742 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9703. Min Act: -0.1700
Data Index: 4835969 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9703. Min Act: -0.1700
Data Index: 8406820 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9703. Min Act: -0.1700
Data Index: 2084747 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9703. Min Act: -0.1700
Data Index: 1739336 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9703. Min Act: -0.1700
Data Index: 8447255 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9391. Min Act: -0.1700
Data Index: 7724458 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9391. Min Act: -0.1700
Data Index: 7668947 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9391. Min Act: -0.1700
Data Index: 5106303 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3453. Min Range: -5.3453
Max Act: 4.9391. Min Act: -0.1700
Data Index: 1419039 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19