Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1284 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.5078. Min Act: -0.1700
Data Index: 1141229 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.3516. Min Act: -0.1700
Data Index: 1831622 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.3203. Min Act: -0.1700
Data Index: 7519120 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.2578. Min Act: -0.1700
Data Index: 826479 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.2578. Min Act: -0.1700
Data Index: 3840816 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.2266. Min Act: -0.1700
Data Index: 2062948 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.2266. Min Act: -0.1700
Data Index: 6657523 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.2578. Min Act: -0.1700
Data Index: 6312689 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.2266. Min Act: -0.1700
Data Index: 1633208 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1641. Min Act: -0.1700
Data Index: 3795036 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1953. Min Act: -0.1700
Data Index: 3903260 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1641. Min Act: -0.1700
Data Index: 273288 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1641. Min Act: -0.1700
Data Index: 2148797 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1641. Min Act: -0.1700
Data Index: 719429 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1328. Min Act: -0.1700
Data Index: 7363858 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1328. Min Act: -0.1700
Data Index: 8328964 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1328. Min Act: -0.1700
Data Index: 5091239 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1016. Min Act: -0.1700
Data Index: 7411021 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1016. Min Act: -0.1700
Data Index: 137381 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5078. Min Range: -5.5078
Max Act: 5.1328. Min Act: -0.1700
Data Index: 2387835 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19