Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4960 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0603. Min Range: -5.0603
Max Act: 5.0603. Min Act: -0.1700
Data Index: 28718 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0603. Min Range: -5.0603
Max Act: 5.0603. Min Act: -0.1700
Data Index: 2320001 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9978. Min Act: -0.1700
Data Index: 1598557 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0603. Min Range: -5.0603
Max Act: 5.0290. Min Act: -0.1700
Data Index: 5192730 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0603. Min Range: -5.0603
Max Act: 5.0290. Min Act: -0.1700
Data Index: 559221 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9665. Min Act: -0.1700
Data Index: 4188994 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9665. Min Act: -0.1700
Data Index: 6931776 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9665. Min Act: -0.1700
Data Index: 8375482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9665. Min Act: -0.1700
Data Index: 1950124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9353. Min Act: -0.1700
Data Index: 1463603 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9353. Min Act: -0.1700
Data Index: 1600908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9353. Min Act: -0.1700
Data Index: 3370698 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9353. Min Act: -0.1700
Data Index: 1200989 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9353. Min Act: -0.1700
Data Index: 726464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9040. Min Act: -0.1700
Data Index: 2167250 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9040. Min Act: -0.1700
Data Index: 7966328 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9040. Min Act: -0.1700
Data Index: 4581234 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.8728. Min Act: -0.1700
Data Index: 5659814 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.9040. Min Act: -0.1700
Data Index: 3068190 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0603. Min Range: -5.0603
Max Act: 4.8728. Min Act: -0.1700
Data Index: 2358331 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19