Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5561 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0903. Min Act: -0.1700
Data Index: 5428222 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0903. Min Act: -0.1700
Data Index: 7803448 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0590. Min Act: -0.1700
Data Index: 5061671 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0903. Min Act: -0.1700
Data Index: 7662261 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0278. Min Act: -0.1700
Data Index: 7451704 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0278. Min Act: -0.1700
Data Index: 13969 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0278. Min Act: -0.1700
Data Index: 2716959 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0278. Min Act: -0.1700
Data Index: 209489 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0278. Min Act: -0.1700
Data Index: 5806040 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 8643713 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 6589444 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 4499005 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 6322002 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 7970891 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 611887 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 426660 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0903. Min Range: -5.0903
Max Act: 5.0278. Min Act: -0.1700
Data Index: 60213 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 5236563 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 59864 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0903. Min Range: -5.0903
Max Act: 4.9965. Min Act: -0.1700
Data Index: 3956987 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19