Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 958 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.6006. Min Act: -0.1700
Data Index: 2110700 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.3506. Min Act: -0.1700
Data Index: 226921 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2881. Min Act: -0.1700
Data Index: 7790973 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2256. Min Act: -0.1700
Data Index: 712663 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2569. Min Act: -0.1700
Data Index: 8434421 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2569. Min Act: -0.1700
Data Index: 3456395 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1944. Min Act: -0.1700
Data Index: 421466 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1631. Min Act: -0.1700
Data Index: 4136758 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1631. Min Act: -0.1700
Data Index: 3498293 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1631. Min Act: -0.1700
Data Index: 3578715 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1319. Min Act: -0.1700
Data Index: 4131246 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1006. Min Act: -0.1700
Data Index: 2833209 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1006. Min Act: -0.1700
Data Index: 7093740 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1006. Min Act: -0.1700
Data Index: 8809848 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.0694. Min Act: -0.1700
Data Index: 6137377 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1006. Min Act: -0.1700
Data Index: 507693 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1006. Min Act: -0.1700
Data Index: 5151682 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.0694. Min Act: -0.1700
Data Index: 5317486 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.0694. Min Act: -0.1700
Data Index: 1915972 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.0069. Min Act: -0.1700
Data Index: 1558376 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19