Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.9619. Min Act: -0.1700
Data Index: 6380624 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.7553. Min Act: -0.1699
Data Index: 1011956 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.7234. Min Act: -0.1700
Data Index: 1535104 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.6914. Min Act: -0.1700
Data Index: 7442932 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.6754. Min Act: -0.1700
Data Index: 4685737 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.6594. Min Act: -0.1700
Data Index: 5449257 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.6594. Min Act: -0.1699
Data Index: 6873317 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.6433. Min Act: -0.1700
Data Index: 7137401 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.6433. Min Act: -0.1700
Data Index: 5323555 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.6112. Min Act: -0.1700
Data Index: 3674587 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5790. Min Act: -0.1699
Data Index: 1784881 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5629. Min Act: -0.1700
Data Index: 3924208 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5467. Min Act: -0.1700
Data Index: 8311384 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5629. Min Act: -0.1700
Data Index: 1749410 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5467. Min Act: -0.1700
Data Index: 1690237 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5306. Min Act: -0.1700
Data Index: 261848 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.4982. Min Act: -0.1695
Data Index: 7590337 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5144. Min Act: -0.1700
Data Index: 6457578 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5306. Min Act: -0.1700
Data Index: 4975299 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9619. Min Range: -2.9619
Max Act: 2.5144. Min Act: -0.1699
Data Index: 7722423 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19