Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4936 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.6436. Min Act: -0.1700
Data Index: 6042649 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.6124. Min Act: -0.1700
Data Index: 7669879 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.6124. Min Act: -0.1700
Data Index: 7669884 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.5499. Min Act: -0.1700
Data Index: 4184239 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.5186. Min Act: -0.1700
Data Index: 8353919 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.4561. Min Act: -0.1700
Data Index: 361906 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.4249. Min Act: -0.1700
Data Index: 622678 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.3624. Min Act: -0.1700
Data Index: 3477816 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.3936. Min Act: -0.1700
Data Index: 8554512 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.3624. Min Act: -0.1700
Data Index: 3034063 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.3624. Min Act: -0.1700
Data Index: 663845 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.3311. Min Act: -0.1700
Data Index: 7793563 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.2686. Min Act: -0.1700
Data Index: 2607858 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.3311. Min Act: -0.1700
Data Index: 435828 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.2686. Min Act: -0.1700
Data Index: 2440044 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.2686. Min Act: -0.1700
Data Index: 5976797 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.2686. Min Act: -0.1700
Data Index: 6580758 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.2374. Min Act: -0.1700
Data Index: 2888443 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.2374. Min Act: -0.1700
Data Index: 4967644 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6436. Min Range: -7.6436
Max Act: 7.1749. Min Act: -0.1700
Data Index: 5143560 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19