Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5568. Min Range: -8.5568
Max Act: 8.5568. Min Act: -0.1700
Data Index: 6725122 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5568. Min Range: -8.5568
Max Act: 8.5568. Min Act: -0.1700
Data Index: 4694710 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5568. Min Range: -8.5568
Max Act: 8.2443. Min Act: -0.1700
Data Index: 7673516 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.9943. Min Act: -0.1700
Data Index: 1825085 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.9943. Min Act: -0.1700
Data Index: 6767947 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5568. Min Range: -8.5568
Max Act: 8.0568. Min Act: -0.1699
Data Index: 4191758 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.9631. Min Act: -0.1694
Data Index: 6767954 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.9318. Min Act: -0.1642
Data Index: 4191756 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.9631. Min Act: -0.1700
Data Index: 147412 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.9318. Min Act: -0.1700
Data Index: 1287596 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.9318. Min Act: -0.1699
Data Index: 6767936 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.8693. Min Act: -0.1700
Data Index: 525851 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.8693. Min Act: -0.1700
Data Index: 5983357 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.8381. Min Act: -0.1700
Data Index: 1063709 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.8068. Min Act: -0.1700
Data Index: 2481882 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.8068. Min Act: -0.1700
Data Index: 5983359 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.7756. Min Act: -0.1700
Data Index: 7771733 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.7756. Min Act: -0.1695
Data Index: 6767939 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.7443. Min Act: -0.1700
Data Index: 3936692 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5568. Min Range: -8.5568
Max Act: 7.7443. Min Act: -0.1688
Data Index: 6767960 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19