Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8748. Min Act: -0.1700
Data Index: 3665417 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8748. Min Act: -0.1700
Data Index: 6173660 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8748. Min Act: -0.1700
Data Index: 4053140 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8435. Min Act: -0.1700
Data Index: 3281352 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8435. Min Act: -0.1700
Data Index: 4466765 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8123. Min Act: -0.1700
Data Index: 7917039 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8123. Min Act: -0.1700
Data Index: 4246542 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8123. Min Act: -0.1700
Data Index: 2107702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8123. Min Act: -0.1700
Data Index: 3665418 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8123. Min Act: -0.1700
Data Index: 7583945 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.8123. Min Act: -0.1700
Data Index: 4857384 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7810. Min Act: -0.1700
Data Index: 2319417 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7810. Min Act: -0.1700
Data Index: 547341 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7810. Min Act: -0.1700
Data Index: 5789649 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7810. Min Act: -0.1700
Data Index: 3892244 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7498. Min Act: -0.1700
Data Index: 4063898 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7185. Min Act: -0.1700
Data Index: 36619 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7498. Min Act: -0.1700
Data Index: 438613 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7185. Min Act: -0.1700
Data Index: 4553575 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8748. Min Range: -4.8748
Max Act: 4.7185. Min Act: -0.1700
Data Index: 6275278 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19