Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1979 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.5436. Min Act: -0.1700
Data Index: 2041330 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.4186. Min Act: -0.1700
Data Index: 4858993 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.3873. Min Act: -0.1700
Data Index: 4461647 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.3561. Min Act: -0.1700
Data Index: 1138088 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.3561. Min Act: -0.1700
Data Index: 768060 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.3248. Min Act: -0.1700
Data Index: 8648485 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.3248. Min Act: -0.1700
Data Index: 4820706 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.3248. Min Act: -0.1700
Data Index: 6485016 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.3248. Min Act: -0.1700
Data Index: 4939387 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2936. Min Act: -0.1700
Data Index: 8648506 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2936. Min Act: -0.1700
Data Index: 448856 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2936. Min Act: -0.1700
Data Index: 457262 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2936. Min Act: -0.1700
Data Index: 2283663 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2936. Min Act: -0.1700
Data Index: 5901965 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2936. Min Act: -0.1700
Data Index: 6436070 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2936. Min Act: -0.1700
Data Index: 3305749 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2623. Min Act: -0.1700
Data Index: 4402628 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2623. Min Act: -0.1700
Data Index: 2102251 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2623. Min Act: -0.1700
Data Index: 2133730 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5436. Min Range: -4.5436
Max Act: 4.2623. Min Act: -0.1700
Data Index: 552645 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19