Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.6109. Min Act: -0.1700
Data Index: 8187600 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.5484. Min Act: -0.1700
Data Index: 6367647 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.5171. Min Act: -0.1700
Data Index: 5867429 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 8414113 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1700
Data Index: 1163375 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1698
Data Index: 387254 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1698
Data Index: 8443320 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1698
Data Index: 4646138 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1700
Data Index: 2518062 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4546. Min Act: -0.1696
Data Index: 5867428 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1700
Data Index: 8447027 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1700
Data Index: 2261243 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.3609. Min Act: -0.1700
Data Index: 7439416 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1698
Data Index: 6845504 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.3921. Min Act: -0.1700
Data Index: 8604380 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.3921. Min Act: -0.1699
Data Index: 6367646 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1700
Data Index: 3272773 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1699
Data Index: 4998139 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.3609. Min Act: -0.1700
Data Index: 308984 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.3609. Min Act: -0.1700
Data Index: 1084763 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19