Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2069 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0401. Min Range: -2.0401
Max Act: 2.0317. Min Act: -0.1697
Data Index: 5555269 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0401. Min Range: -2.0401
Max Act: 2.0401. Min Act: -0.1700
Data Index: 1711563 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0401. Min Range: -2.0401
Max Act: 2.0233. Min Act: -0.1693
Data Index: 2384531 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0401. Min Range: -2.0401
Max Act: 2.0233. Min Act: -0.1699
Data Index: 7824693 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9811. Min Act: -0.1700
Data Index: 1521191 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9726. Min Act: -0.1700
Data Index: 6461740 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9811. Min Act: -0.1700
Data Index: 5687500 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9726. Min Act: -0.1700
Data Index: 5327941 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9811. Min Act: -0.1700
Data Index: 7278615 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9641. Min Act: -0.1700
Data Index: 2675283 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9641. Min Act: -0.1700
Data Index: 5318723 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9641. Min Act: -0.1700
Data Index: 4711367 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9641. Min Act: -0.1700
Data Index: 1786242 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9641. Min Act: -0.1700
Data Index: 4004717 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9641. Min Act: -0.1700
Data Index: 999796 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9641. Min Act: -0.1700
Data Index: 2559615 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9556. Min Act: -0.1700
Data Index: 7599944 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9556. Min Act: -0.1700
Data Index: 797522 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9556. Min Act: -0.1700
Data Index: 5793840 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0401. Min Range: -2.0401
Max Act: 1.9641. Min Act: -0.1700
Data Index: 2809296 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19