Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.9891. Min Act: -0.1700
Data Index: 1980188 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.9422. Min Act: -0.1700
Data Index: 7915048 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.9265. Min Act: -0.1700
Data Index: 5785568 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.9109. Min Act: -0.1700
Data Index: 7915044 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8796. Min Act: -0.1700
Data Index: 7214119 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8953. Min Act: -0.1700
Data Index: 7214126 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8796. Min Act: -0.1700
Data Index: 7443512 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8484. Min Act: -0.1700
Data Index: 2811812 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8484. Min Act: -0.1700
Data Index: 2216901 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8327. Min Act: -0.1700
Data Index: 5704686 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8171. Min Act: -0.1700
Data Index: 4496740 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.7858. Min Act: -0.1700
Data Index: 7724218 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.7858. Min Act: -0.1700
Data Index: 1163019 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8015. Min Act: -0.1700
Data Index: 3481828 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.8015. Min Act: -0.1700
Data Index: 3067354 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.7858. Min Act: -0.1700
Data Index: 7066131 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.7858. Min Act: -0.1700
Data Index: 3481831 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.7858. Min Act: -0.1700
Data Index: 6240191 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.7858. Min Act: -0.1700
Data Index: 5704693 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9891. Min Range: -3.9891
Max Act: 3.7702. Min Act: -0.1700
Data Index: 5632473 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19