Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5484 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7711. Min Range: -6.7711
Max Act: 6.7711. Min Act: -0.1700
Data Index: 3779828 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7711. Min Range: -6.7711
Max Act: 6.3961. Min Act: -0.1700
Data Index: 8304964 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7711. Min Range: -6.7711
Max Act: 6.3024. Min Act: -0.1700
Data Index: 8769636 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7711. Min Range: -6.7711
Max Act: 6.1774. Min Act: -0.1700
Data Index: 4336985 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7711. Min Range: -6.7711
Max Act: 6.1461. Min Act: -0.1700
Data Index: 1396538 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.9586. Min Act: -0.1700
Data Index: 5651587 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.9274. Min Act: -0.1700
Data Index: 1240487 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.8649. Min Act: -0.1700
Data Index: 7043691 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.8336. Min Act: -0.1700
Data Index: 4669509 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.8336. Min Act: -0.1700
Data Index: 179850 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7711. Min Act: -0.1700
Data Index: 5163329 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7711. Min Act: -0.1700
Data Index: 3460913 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7711. Min Act: -0.1700
Data Index: 601104 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7711. Min Act: -0.1700
Data Index: 7061589 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7399. Min Act: -0.1700
Data Index: 3712682 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7399. Min Act: -0.1700
Data Index: 239185 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7086. Min Act: -0.1700
Data Index: 2502464 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7086. Min Act: -0.1700
Data Index: 5311899 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7086. Min Act: -0.1700
Data Index: 8357601 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7711. Min Range: -6.7711
Max Act: 5.7399. Min Act: -0.1700
Data Index: 2522741 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19