Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4411 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2456. Min Act: -0.1700
Data Index: 7256175 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2456. Min Act: -0.1700
Data Index: 1469611 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2456. Min Act: -0.1700
Data Index: 7036295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2456. Min Act: -0.1700
Data Index: 5210178 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2143. Min Act: -0.1699
Data Index: 2875623 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1831. Min Act: -0.1700
Data Index: 5331098 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2143. Min Act: -0.1700
Data Index: 1531261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1831. Min Act: -0.1700
Data Index: 8037195 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1831. Min Act: -0.1700
Data Index: 7710518 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1831. Min Act: -0.1700
Data Index: 7806680 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1518. Min Act: -0.1700
Data Index: 5168279 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1518. Min Act: -0.1700
Data Index: 2027925 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1518. Min Act: -0.1700
Data Index: 219720 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1518. Min Act: -0.1700
Data Index: 8356944 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1205. Min Act: -0.1700
Data Index: 3372478 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1518. Min Act: -0.1700
Data Index: 8136829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1205. Min Act: -0.1700
Data Index: 6223180 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1205. Min Act: -0.1700
Data Index: 4404294 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1205. Min Act: -0.1700
Data Index: 7194137 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1205. Min Act: -0.1700
Data Index: 150045 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19