Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.8638. Min Act: -0.1700
Data Index: 1989368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.8013. Min Act: -0.1700
Data Index: 3408310 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.8325. Min Act: -0.1700
Data Index: 984772 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.8325. Min Act: -0.1700
Data Index: 3081967 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7700. Min Act: -0.1700
Data Index: 5611667 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7700. Min Act: -0.1700
Data Index: 2913772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7700. Min Act: -0.1700
Data Index: 3676269 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7700. Min Act: -0.1700
Data Index: 1905243 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7700. Min Act: -0.1700
Data Index: 3081982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7388. Min Act: -0.1700
Data Index: 6376429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7388. Min Act: -0.1700
Data Index: 1327985 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7388. Min Act: -0.1700
Data Index: 8648284 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7388. Min Act: -0.1700
Data Index: 7783715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7700. Min Act: -0.1700
Data Index: 7251274 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7388. Min Act: -0.1700
Data Index: 7148209 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7388. Min Act: -0.1700
Data Index: 1873030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7388. Min Act: -0.1700
Data Index: 7018524 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7388. Min Act: -0.1700
Data Index: 6675975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7075. Min Act: -0.1700
Data Index: 2292990 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8638. Min Range: -5.8638
Max Act: 5.7075. Min Act: -0.1700
Data Index: 4339678 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19