Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1108 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1404. Min Range: -6.1404
Max Act: 6.1404. Min Act: -0.1700
Data Index: 8450480 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1404. Min Range: -6.1404
Max Act: 6.1404. Min Act: -0.1700
Data Index: 1736296 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1404. Min Range: -6.1404
Max Act: 6.0779. Min Act: -0.1700
Data Index: 3346351 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1404. Min Range: -6.1404
Max Act: 6.0467. Min Act: -0.1700
Data Index: 1205741 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1404. Min Range: -6.1404
Max Act: 6.0154. Min Act: -0.1700
Data Index: 7269483 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1404. Min Range: -6.1404
Max Act: 6.0154. Min Act: -0.1700
Data Index: 8705036 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1404. Min Range: -6.1404
Max Act: 6.0154. Min Act: -0.1700
Data Index: 1909230 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9842. Min Act: -0.1700
Data Index: 2512168 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9842. Min Act: -0.1700
Data Index: 2902948 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9842. Min Act: -0.1700
Data Index: 1120528 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9529. Min Act: -0.1700
Data Index: 6651484 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9217. Min Act: -0.1700
Data Index: 4223601 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9529. Min Act: -0.1700
Data Index: 478162 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9529. Min Act: -0.1700
Data Index: 3070949 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9529. Min Act: -0.1700
Data Index: 2457504 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9529. Min Act: -0.1700
Data Index: 8074797 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9529. Min Act: -0.1700
Data Index: 820213 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9529. Min Act: -0.1700
Data Index: 6117614 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.9217. Min Act: -0.1700
Data Index: 5508036 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1404. Min Range: -6.1404
Max Act: 5.8904. Min Act: -0.1700
Data Index: 472534 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19