Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6084 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.9834. Min Act: -0.1700
Data Index: 751904 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.8584. Min Act: -0.1699
Data Index: 1627763 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.8584. Min Act: -0.1700
Data Index: 7024581 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.8271. Min Act: -0.1700
Data Index: 8661579 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.8271. Min Act: -0.1700
Data Index: 4149881 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.8271. Min Act: -0.1700
Data Index: 1362263 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7646. Min Act: -0.1700
Data Index: 5570181 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7959. Min Act: -0.1700
Data Index: 5731715 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7646. Min Act: -0.1700
Data Index: 5036395 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7646. Min Act: -0.1700
Data Index: 5726853 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7646. Min Act: -0.1700
Data Index: 1203621 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7646. Min Act: -0.1700
Data Index: 5749360 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7334. Min Act: -0.1700
Data Index: 810570 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7334. Min Act: -0.1699
Data Index: 3275814 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7334. Min Act: -0.1700
Data Index: 2739641 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7334. Min Act: -0.1700
Data Index: 7587606 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7334. Min Act: -0.1700
Data Index: 6258126 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7334. Min Act: -0.1696
Data Index: 1554317 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7334. Min Act: -0.1700
Data Index: 284256 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9834. Min Range: -4.9834
Max Act: 4.7021. Min Act: -0.1700
Data Index: 561415 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19