Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1696. Min Range: -1.1696
Max Act: 1.1696. Min Act: -0.1700
Data Index: 7177531 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1696. Min Range: -1.1696
Max Act: 1.1170. Min Act: -0.1700
Data Index: 5900965 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1696. Min Range: -1.1696
Max Act: 1.0907. Min Act: -0.1700
Data Index: 755330 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1696. Min Range: -1.1696
Max Act: 1.0819. Min Act: -0.1700
Data Index: 2541679 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1696. Min Range: -1.1696
Max Act: 1.0209. Min Act: -0.1700
Data Index: 2541676 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9861. Min Act: -0.1700
Data Index: 2541674 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9602. Min Act: -0.1700
Data Index: 2541680 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9688. Min Act: -0.1700
Data Index: 3384923 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9602. Min Act: -0.1700
Data Index: 2541675 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9516. Min Act: -0.1700
Data Index: 7563658 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9343. Min Act: -0.1700
Data Index: 895227 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9257. Min Act: -0.1700
Data Index: 1894877 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9257. Min Act: -0.1700
Data Index: 384715 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9257. Min Act: -0.1700
Data Index: 895226 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9257. Min Act: -0.1700
Data Index: 2936814 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9171. Min Act: -0.1700
Data Index: 1787757 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9171. Min Act: -0.1700
Data Index: 384714 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.9086. Min Act: -0.1694
Data Index: 6656714 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.8915. Min Act: -0.1700
Data Index: 2541678 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1696. Min Range: -1.1696
Max Act: 0.8915. Min Act: -0.1700
Data Index: 6272525 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19