Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6824. Min Range: -9.6824
Max Act: 9.6824. Min Act: -0.1700
Data Index: 4858826 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6824. Min Range: -9.6824
Max Act: 9.5574. Min Act: -0.1700
Data Index: 4858824 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6824. Min Range: -9.6824
Max Act: 9.3074. Min Act: -0.1700
Data Index: 8071681 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6824. Min Range: -9.6824
Max Act: 9.1199. Min Act: -0.1700
Data Index: 1430359 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6824. Min Range: -9.6824
Max Act: 9.0574. Min Act: -0.1700
Data Index: 5862610 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6824. Min Range: -9.6824
Max Act: 9.0574. Min Act: -0.1700
Data Index: 1201881 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.9949. Min Act: -0.1700
Data Index: 4564999 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.9949. Min Act: -0.1700
Data Index: 7186659 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.9949. Min Act: -0.1700
Data Index: 7487596 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.8699. Min Act: -0.1700
Data Index: 3816016 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.8074. Min Act: -0.1700
Data Index: 4417595 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.6824. Min Act: -0.1700
Data Index: 5484962 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.7449. Min Act: -0.1700
Data Index: 1408815 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.7449. Min Act: -0.1700
Data Index: 6430321 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.7449. Min Act: -0.1700
Data Index: 7898909 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.5574. Min Act: -0.1700
Data Index: 4000910 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 1127449 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 2677722 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 3562721 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6824. Min Range: -9.6824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 2170609 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19