Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1549 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.9920. Min Act: -0.1700
Data Index: 6181179 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.9607. Min Act: -0.1700
Data Index: 1743617 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.8045. Min Act: -0.1700
Data Index: 788114 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.7732. Min Act: -0.1700
Data Index: 632603 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.6795. Min Act: -0.1700
Data Index: 5668933 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.6795. Min Act: -0.1700
Data Index: 1481481 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.6482. Min Act: -0.1700
Data Index: 417536 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.6482. Min Act: -0.1700
Data Index: 540110 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.6170. Min Act: -0.1700
Data Index: 2930711 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.6170. Min Act: -0.1700
Data Index: 8494887 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.6170. Min Act: -0.1700
Data Index: 8380877 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5857. Min Act: -0.1700
Data Index: 2944014 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5857. Min Act: -0.1700
Data Index: 6250163 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5857. Min Act: -0.1700
Data Index: 6746842 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5545. Min Act: -0.1700
Data Index: 4228529 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5545. Min Act: -0.1700
Data Index: 4274713 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5545. Min Act: -0.1700
Data Index: 7794212 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5545. Min Act: -0.1700
Data Index: 5822415 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5545. Min Act: -0.1700
Data Index: 3618170 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9920. Min Range: -4.9920
Max Act: 4.5545. Min Act: -0.1700
Data Index: 2764866 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19