Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.8588. Min Act: -0.1700
Data Index: 8427593 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.7650. Min Act: -0.1700
Data Index: 6733550 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.5775. Min Act: -0.1700
Data Index: 1254578 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.5775. Min Act: -0.1700
Data Index: 1254584 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.3275. Min Act: -0.1700
Data Index: 8427594 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.2650. Min Act: -0.1700
Data Index: 279405 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.2650. Min Act: -0.1700
Data Index: 8427607 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.2025. Min Act: -0.1700
Data Index: 7148200 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.1400. Min Act: -0.1700
Data Index: 2425729 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.0463. Min Act: -0.1700
Data Index: 2343933 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.0463. Min Act: -0.1700
Data Index: 8275329 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8588. Min Range: -6.8588
Max Act: 6.0150. Min Act: -0.1700
Data Index: 2200976 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8588. Min Range: -6.8588
Max Act: 5.9838. Min Act: -0.1700
Data Index: 4442278 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8588. Min Range: -6.8588
Max Act: 5.9525. Min Act: -0.1700
Data Index: 2273216 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8588. Min Range: -6.8588
Max Act: 5.9525. Min Act: -0.1700
Data Index: 5678298 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8588. Min Range: -6.8588
Max Act: 5.9213. Min Act: -0.1700
Data Index: 1106522 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8588. Min Range: -6.8588
Max Act: 5.8900. Min Act: -0.1700
Data Index: 933050 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8588. Min Range: -6.8588
Max Act: 5.9213. Min Act: -0.1700
Data Index: 1254583 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8588. Min Range: -6.8588
Max Act: 5.8588. Min Act: -0.1700
Data Index: 1464542 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8588. Min Range: -6.8588
Max Act: 5.8275. Min Act: -0.1700
Data Index: 2560809 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19