Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9693. Min Act: -0.1700
Data Index: 6813449 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9380. Min Act: -0.1700
Data Index: 1511766 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9068. Min Act: -0.1700
Data Index: 4170284 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8755. Min Act: -0.1700
Data Index: 7234130 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8443. Min Act: -0.1700
Data Index: 1880761 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8443. Min Act: -0.1700
Data Index: 3268066 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8130. Min Act: -0.1700
Data Index: 425459 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8130. Min Act: -0.1700
Data Index: 7335077 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7505. Min Act: -0.1700
Data Index: 2472562 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7505. Min Act: -0.1700
Data Index: 2823008 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7505. Min Act: -0.1700
Data Index: 7240656 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7193. Min Act: -0.1700
Data Index: 5755486 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6880. Min Act: -0.1700
Data Index: 1034316 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 8752332 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 7660792 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 945644 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6255. Min Act: -0.1700
Data Index: 5773739 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6255. Min Act: -0.1700
Data Index: 4510929 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6255. Min Act: -0.1700
Data Index: 68665 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5943. Min Act: -0.1700
Data Index: 666716 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19