Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.8258. Min Act: -0.1700
Data Index: 2434238 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.8258. Min Act: -0.1700
Data Index: 1070383 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.8571. Min Act: -0.1700
Data Index: 1775478 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7946. Min Act: -0.1700
Data Index: 3313676 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7633. Min Act: -0.1700
Data Index: 1150326 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7633. Min Act: -0.1700
Data Index: 3395576 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7633. Min Act: -0.1700
Data Index: 5265287 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 1407925 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 8511358 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 3647197 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7008. Min Act: -0.1700
Data Index: 1623342 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 5889395 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7321. Min Act: -0.1700
Data Index: 7840179 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7008. Min Act: -0.1700
Data Index: 3017044 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7008. Min Act: -0.1700
Data Index: 1644573 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.6696. Min Act: -0.1700
Data Index: 1802175 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.6696. Min Act: -0.1700
Data Index: 8047084 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.7008. Min Act: -0.1700
Data Index: 2796938 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.6696. Min Act: -0.1700
Data Index: 7496904 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8571. Min Range: -4.8571
Max Act: 4.6696. Min Act: -0.1700
Data Index: 5862565 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19