Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.8310. Min Act: -0.1700
Data Index: 4318053 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.4560. Min Act: -0.1700
Data Index: 848362 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.3935. Min Act: -0.1700
Data Index: 1616162 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.3310. Min Act: -0.1700
Data Index: 4527861 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.2685. Min Act: -0.1700
Data Index: 5260504 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.2685. Min Act: -0.1700
Data Index: 4866055 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.3310. Min Act: -0.1700
Data Index: 3822332 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.2060. Min Act: -0.1700
Data Index: 13183 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.2060. Min Act: -0.1700
Data Index: 6630279 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.2060. Min Act: -0.1700
Data Index: 6308195 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.2060. Min Act: -0.1700
Data Index: 1681052 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.1435. Min Act: -0.1700
Data Index: 5041972 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.1435. Min Act: -0.1700
Data Index: 8283758 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.0810. Min Act: -0.1700
Data Index: 365270 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.0810. Min Act: -0.1700
Data Index: 1003746 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.0810. Min Act: -0.1700
Data Index: 5535222 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.0810. Min Act: -0.1700
Data Index: 4591790 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.0810. Min Act: -0.1700
Data Index: 5516966 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.0810. Min Act: -0.1700
Data Index: 7262690 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8310. Min Range: -8.8310
Max Act: 8.0810. Min Act: -0.1700
Data Index: 5266598 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19