Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1118 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3317. Min Range: -8.3317
Max Act: 8.3317. Min Act: -0.1700
Data Index: 2612370 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3317. Min Range: -8.3317
Max Act: 8.0817. Min Act: -0.1700
Data Index: 3356764 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3317. Min Range: -8.3317
Max Act: 8.0817. Min Act: -0.1700
Data Index: 1809224 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3317. Min Range: -8.3317
Max Act: 8.0192. Min Act: -0.1700
Data Index: 3485582 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3317. Min Range: -8.3317
Max Act: 8.0192. Min Act: -0.1700
Data Index: 8783065 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3317. Min Range: -8.3317
Max Act: 8.0817. Min Act: -0.1700
Data Index: 6558618 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.9567. Min Act: -0.1700
Data Index: 5950852 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.9567. Min Act: -0.1700
Data Index: 7982935 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8942. Min Act: -0.1700
Data Index: 4159498 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8942. Min Act: -0.1700
Data Index: 8285021 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8942. Min Act: -0.1700
Data Index: 4632552 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8942. Min Act: -0.1700
Data Index: 6857911 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8942. Min Act: -0.1700
Data Index: 864123 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8317. Min Act: -0.1700
Data Index: 6066173 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8317. Min Act: -0.1700
Data Index: 7695566 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8317. Min Act: -0.1700
Data Index: 1702833 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8317. Min Act: -0.1700
Data Index: 8503497 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.8317. Min Act: -0.1700
Data Index: 8763383 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.7692. Min Act: -0.1700
Data Index: 4693115 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3317. Min Range: -8.3317
Max Act: 7.7692. Min Act: -0.1700
Data Index: 3928532 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19