Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.5818. Min Act: -0.1700
Data Index: 3307200 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.2693. Min Act: -0.1700
Data Index: 1475198 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.3006. Min Act: -0.1700
Data Index: 1499808 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.3006. Min Act: -0.1700
Data Index: 350961 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.3006. Min Act: -0.1700
Data Index: 6191608 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.2693. Min Act: -0.1700
Data Index: 5725001 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.2381. Min Act: -0.1700
Data Index: 7922143 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.2381. Min Act: -0.1700
Data Index: 8811475 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.2381. Min Act: -0.1700
Data Index: 5092911 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.2068. Min Act: -0.1700
Data Index: 5613226 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.2068. Min Act: -0.1700
Data Index: 1027560 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1756. Min Act: -0.1700
Data Index: 2132905 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1131. Min Act: -0.1700
Data Index: 1165267 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1443. Min Act: -0.1700
Data Index: 6435768 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1443. Min Act: -0.1700
Data Index: 350967 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1756. Min Act: -0.1700
Data Index: 3079400 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1131. Min Act: -0.1700
Data Index: 1743744 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1131. Min Act: -0.1700
Data Index: 5867853 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1131. Min Act: -0.1700
Data Index: 3901589 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5818. Min Range: -5.5818
Max Act: 5.1131. Min Act: -0.1700
Data Index: 5320627 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19