Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 942 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.6754. Min Act: -0.1700
Data Index: 5843318 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.6442. Min Act: -0.1700
Data Index: 5673605 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.6129. Min Act: -0.1700
Data Index: 3692305 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.6129. Min Act: -0.1700
Data Index: 1814764 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5817. Min Act: -0.1700
Data Index: 6768627 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5504. Min Act: -0.1700
Data Index: 2947467 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5504. Min Act: -0.1700
Data Index: 8224289 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5504. Min Act: -0.1700
Data Index: 5918527 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5192. Min Act: -0.1700
Data Index: 7609748 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5192. Min Act: -0.1700
Data Index: 2734916 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.4879. Min Act: -0.1700
Data Index: 7050044 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5192. Min Act: -0.1700
Data Index: 1863131 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5192. Min Act: -0.1700
Data Index: 3171827 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5192. Min Act: -0.1700
Data Index: 681409 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.5192. Min Act: -0.1700
Data Index: 4426787 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.4879. Min Act: -0.1700
Data Index: 4984630 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.4879. Min Act: -0.1700
Data Index: 6141204 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.4879. Min Act: -0.1700
Data Index: 6182650 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.4879. Min Act: -0.1700
Data Index: 5945682 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6754. Min Range: -5.6754
Max Act: 5.4879. Min Act: -0.1700
Data Index: 1554376 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19