Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.6343. Min Act: -0.1700
Data Index: 8292591 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.5718. Min Act: -0.1700
Data Index: 1594959 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.5405. Min Act: -0.1700
Data Index: 5375016 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.5093. Min Act: -0.1700
Data Index: 6121490 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.5093. Min Act: -0.1700
Data Index: 2443524 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.4780. Min Act: -0.1700
Data Index: 7729137 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.4468. Min Act: -0.1700
Data Index: 8711333 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.4155. Min Act: -0.1700
Data Index: 6737065 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.3843. Min Act: -0.1700
Data Index: 487978 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.3218. Min Act: -0.1700
Data Index: 7562854 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.3218. Min Act: -0.1700
Data Index: 3764484 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.3218. Min Act: -0.1700
Data Index: 712101 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.3218. Min Act: -0.1700
Data Index: 6192629 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.3218. Min Act: -0.1700
Data Index: 2513156 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.2905. Min Act: -0.1700
Data Index: 1615826 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.2593. Min Act: -0.1700
Data Index: 3514962 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.1968. Min Act: -0.1700
Data Index: 7353174 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.2280. Min Act: -0.1700
Data Index: 244178 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.1968. Min Act: -0.1700
Data Index: 1794099 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6343. Min Range: -5.6343
Max Act: 5.1968. Min Act: -0.1700
Data Index: 3784661 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19