Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1545 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.2702. Min Act: -0.1700
Data Index: 1484873 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.2077. Min Act: -0.1700
Data Index: 7712703 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.1452. Min Act: -0.1700
Data Index: 2824947 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.1452. Min Act: -0.1700
Data Index: 8622585 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.1452. Min Act: -0.1700
Data Index: 1586622 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.0827. Min Act: -0.1700
Data Index: 1072233 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.0202. Min Act: -0.1700
Data Index: 291375 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.0827. Min Act: -0.1700
Data Index: 8086072 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.0202. Min Act: -0.1700
Data Index: 2575155 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.0202. Min Act: -0.1700
Data Index: 5029606 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.0202. Min Act: -0.1700
Data Index: 2858312 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.0202. Min Act: -0.1700
Data Index: 8608862 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2702. Min Range: -10.2702
Max Act: 10.0202. Min Act: -0.1700
Data Index: 357705 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2702. Min Range: -10.2702
Max Act: 9.9577. Min Act: -0.1700
Data Index: 3279599 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2702. Min Range: -10.2702
Max Act: 9.9577. Min Act: -0.1700
Data Index: 3133461 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2702. Min Range: -10.2702
Max Act: 9.9577. Min Act: -0.1700
Data Index: 5821658 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2702. Min Range: -10.2702
Max Act: 9.9577. Min Act: -0.1700
Data Index: 6032366 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2702. Min Range: -10.2702
Max Act: 9.9577. Min Act: -0.1700
Data Index: 6571885 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2702. Min Range: -10.2702
Max Act: 9.9577. Min Act: -0.1700
Data Index: 4337365 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2702. Min Range: -10.2702
Max Act: 9.9577. Min Act: -0.1700
Data Index: 1124827 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19