Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3124 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.3516. Min Act: -0.1700
Data Index: 1516164 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.3203. Min Act: -0.1700
Data Index: 8681810 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.2891. Min Act: -0.1700
Data Index: 51912 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.2891. Min Act: -0.1700
Data Index: 3058446 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.2578. Min Act: -0.1700
Data Index: 14972 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.2891. Min Act: -0.1700
Data Index: 1452257 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.2266. Min Act: -0.1700
Data Index: 4527422 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.1953. Min Act: -0.1700
Data Index: 3726714 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.1641. Min Act: -0.1700
Data Index: 430549 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.1328. Min Act: -0.1700
Data Index: 658949 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.1016. Min Act: -0.1700
Data Index: 6561475 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0703. Min Act: -0.1700
Data Index: 8542877 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0703. Min Act: -0.1700
Data Index: 6786920 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0703. Min Act: -0.1700
Data Index: 2159854 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0391. Min Act: -0.1700
Data Index: 6567112 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0391. Min Act: -0.1700
Data Index: 4146915 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0391. Min Act: -0.1700
Data Index: 8033144 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0391. Min Act: -0.1700
Data Index: 7215253 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0391. Min Act: -0.1700
Data Index: 5494319 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3516. Min Range: -6.3516
Max Act: 6.0078. Min Act: -0.1700
Data Index: 1874298 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19