Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2611 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.9651. Min Act: -0.1700
Data Index: 2473282 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.6839. Min Act: -0.1700
Data Index: 3110132 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.6526. Min Act: -0.1700
Data Index: 8124023 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.6214. Min Act: -0.1700
Data Index: 6156466 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.6214. Min Act: -0.1700
Data Index: 6896296 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.5589. Min Act: -0.1700
Data Index: 101894 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.5276. Min Act: -0.1700
Data Index: 6286367 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.5276. Min Act: -0.1700
Data Index: 4194051 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.4964. Min Act: -0.1700
Data Index: 4091409 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.4651. Min Act: -0.1700
Data Index: 4928723 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.4651. Min Act: -0.1700
Data Index: 4100640 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.4026. Min Act: -0.1700
Data Index: 8348309 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.4026. Min Act: -0.1700
Data Index: 5119854 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.4026. Min Act: -0.1700
Data Index: 1068143 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.3714. Min Act: -0.1700
Data Index: 112760 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.3714. Min Act: -0.1700
Data Index: 2454016 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.3401. Min Act: -0.1700
Data Index: 6884359 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.3089. Min Act: -0.1700
Data Index: 7886948 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.3089. Min Act: -0.1700
Data Index: 2873291 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9651. Min Range: -6.9651
Max Act: 6.3089. Min Act: -0.1700
Data Index: 170862 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19