Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 335 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.7642. Min Act: -0.1700
Data Index: 4556578 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.6705. Min Act: -0.1700
Data Index: 6527607 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.7330. Min Act: -0.1700
Data Index: 5617721 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.6392. Min Act: -0.1700
Data Index: 6029414 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.6080. Min Act: -0.1700
Data Index: 7964188 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.6080. Min Act: -0.1700
Data Index: 7058227 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.6080. Min Act: -0.1700
Data Index: 7032856 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.6080. Min Act: -0.1700
Data Index: 6341792 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.5767. Min Act: -0.1700
Data Index: 3477210 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.5767. Min Act: -0.1700
Data Index: 8564594 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.6080. Min Act: -0.1700
Data Index: 946562 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.5767. Min Act: -0.1700
Data Index: 1355434 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.5455. Min Act: -0.1700
Data Index: 723304 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.5455. Min Act: -0.1700
Data Index: 7275073 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.5455. Min Act: -0.1700
Data Index: 4384354 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.5142. Min Act: -0.1700
Data Index: 3453674 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.5142. Min Act: -0.1700
Data Index: 1940206 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.4830. Min Act: -0.1700
Data Index: 5828985 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.4830. Min Act: -0.1700
Data Index: 814660 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7642. Min Range: -4.7642
Max Act: 4.4830. Min Act: -0.1700
Data Index: 2490444 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19