Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.8623. Min Act: -0.1700
Data Index: 8506057 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.6545. Min Act: -0.1700
Data Index: 2961109 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5865. Min Act: -0.1700
Data Index: 3452099 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5201. Min Act: -0.1700
Data Index: 3970287 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5059. Min Act: -0.1700
Data Index: 3608430 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5313. Min Act: -0.1700
Data Index: 8107920 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5035. Min Act: -0.1700
Data Index: 4155436 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5134. Min Act: -0.1700
Data Index: 2506212 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4913. Min Act: -0.1700
Data Index: 7647809 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4745. Min Act: -0.1700
Data Index: 5139785 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4778. Min Act: -0.1700
Data Index: 3165182 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4716. Min Act: -0.1700
Data Index: 1094614 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4636. Min Act: -0.1700
Data Index: 829720 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4674. Min Act: -0.1700
Data Index: 1793154 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4680. Min Act: -0.1700
Data Index: 8405054 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4558. Min Act: -0.1700
Data Index: 5101617 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4509. Min Act: -0.1700
Data Index: 268040 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4193. Min Act: -0.1700
Data Index: 2140281 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4427. Min Act: -0.1700
Data Index: 7040695 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.4366. Min Act: -0.1700
Data Index: 4659065 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full textTruncated
Full Text #19