Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5864 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.2941. Min Act: -0.1700
Data Index: 1024598 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.2588. Min Act: -0.1700
Data Index: 5985142 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.2059. Min Act: -0.1700
Data Index: 8277869 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.2059. Min Act: -0.1700
Data Index: 362897 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.2059. Min Act: -0.1700
Data Index: 1639683 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1883. Min Act: -0.1700
Data Index: 8384048 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1531. Min Act: -0.1700
Data Index: 1613983 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1707. Min Act: -0.1700
Data Index: 6260138 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1531. Min Act: -0.1700
Data Index: 3563465 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1531. Min Act: -0.1700
Data Index: 4685401 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1531. Min Act: -0.1700
Data Index: 64399 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1531. Min Act: -0.1700
Data Index: 2269074 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1356. Min Act: -0.1700
Data Index: 7010095 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1356. Min Act: -0.1700
Data Index: 6659735 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1356. Min Act: -0.1700
Data Index: 1702752 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1356. Min Act: -0.1700
Data Index: 3195173 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1531. Min Act: -0.1700
Data Index: 182913 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1356. Min Act: -0.1700
Data Index: 379527 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1356. Min Act: -0.1700
Data Index: 1877998 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2941. Min Range: -1.2941
Max Act: 1.1356. Min Act: -0.1700
Data Index: 5740251 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19