Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.8843. Min Act: -0.1700
Data Index: 3962930 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.6968. Min Act: -0.1700
Data Index: 3486398 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.5093. Min Act: -0.1700
Data Index: 6004528 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.4468. Min Act: -0.1700
Data Index: 6892547 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.3218. Min Act: -0.1700
Data Index: 8515829 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.2593. Min Act: -0.1700
Data Index: 1260028 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1968. Min Act: -0.1700
Data Index: 3552945 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1968. Min Act: -0.1700
Data Index: 1968097 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1968. Min Act: -0.1700
Data Index: 6535906 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1968. Min Act: -0.1700
Data Index: 8428084 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1343. Min Act: -0.1700
Data Index: 1814467 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1343. Min Act: -0.1700
Data Index: 4779363 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1343. Min Act: -0.1700
Data Index: 2198952 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1343. Min Act: -0.1700
Data Index: 1282013 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.0718. Min Act: -0.1700
Data Index: 6513624 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1343. Min Act: -0.1700
Data Index: 539487 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.0718. Min Act: -0.1700
Data Index: 1157582 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.0718. Min Act: -0.1700
Data Index: 3136114 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.1343. Min Act: -0.1700
Data Index: 4604073 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8843. Min Range: -8.8843
Max Act: 8.0718. Min Act: -0.1700
Data Index: 5517388 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19