Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7256. Min Range: -11.7256
Max Act: 11.7256. Min Act: -0.1700
Data Index: 2951293 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7256. Min Range: -11.7256
Max Act: 11.1631. Min Act: -0.1700
Data Index: 8363726 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7256. Min Range: -11.7256
Max Act: 11.1006. Min Act: -0.1700
Data Index: 3104914 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7256. Min Range: -11.7256
Max Act: 10.4756. Min Act: -0.1700
Data Index: 1622660 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7256. Min Range: -11.7256
Max Act: 10.3506. Min Act: -0.1700
Data Index: 3154905 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7256. Min Range: -11.7256
Max Act: 10.3506. Min Act: -0.1700
Data Index: 1405404 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7256. Min Range: -11.7256
Max Act: 10.2256. Min Act: -0.1700
Data Index: 1831177 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7256. Min Range: -11.7256
Max Act: 10.1631. Min Act: -0.1700
Data Index: 1571552 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7256. Min Range: -11.7256
Max Act: 10.1006. Min Act: -0.1700
Data Index: 3704755 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7256. Min Range: -11.7256
Max Act: 10.0381. Min Act: -0.1700
Data Index: 4812725 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.9756. Min Act: -0.1700
Data Index: 5646744 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.9756. Min Act: -0.1700
Data Index: 4997163 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.9131. Min Act: -0.1700
Data Index: 5243262 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.9756. Min Act: -0.1700
Data Index: 6971925 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.9131. Min Act: -0.1700
Data Index: 8364981 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.8506. Min Act: -0.1700
Data Index: 2751341 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.7881. Min Act: -0.1699
Data Index: 5758013 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.7881. Min Act: -0.1700
Data Index: 2047297 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.7881. Min Act: -0.1700
Data Index: 4135377 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7256. Min Range: -11.7256
Max Act: 9.7881. Min Act: -0.1700
Data Index: 7560162 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19