Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5874 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2637. Min Range: -9.2637
Max Act: 9.2637. Min Act: -0.1700
Data Index: 7789811 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8887. Min Act: -0.1700
Data Index: 5335657 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8262. Min Act: -0.1700
Data Index: 7433430 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8887. Min Act: -0.1700
Data Index: 7676241 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8262. Min Act: -0.1700
Data Index: 142005 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8262. Min Act: -0.1700
Data Index: 6753579 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8262. Min Act: -0.1700
Data Index: 7905444 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8887. Min Act: -0.1700
Data Index: 2037457 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8262. Min Act: -0.1700
Data Index: 1976674 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.7637. Min Act: -0.1700
Data Index: 5623669 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.7637. Min Act: -0.1700
Data Index: 4599947 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.8262. Min Act: -0.1700
Data Index: 7300419 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.7012. Min Act: -0.1700
Data Index: 3177804 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.6387. Min Act: -0.1700
Data Index: 8779143 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.6387. Min Act: -0.1700
Data Index: 8639141 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.6387. Min Act: -0.1700
Data Index: 3975529 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.6387. Min Act: -0.1700
Data Index: 2037803 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.6387. Min Act: -0.1700
Data Index: 6309119 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.5762. Min Act: -0.1700
Data Index: 5773843 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2637. Min Range: -9.2637
Max Act: 8.5762. Min Act: -0.1700
Data Index: 2127687 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19