Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.8306. Min Act: -0.1700
Data Index: 6713187 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.6119. Min Act: -0.1700
Data Index: 2987250 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.5806. Min Act: -0.1700
Data Index: 7963982 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.5806. Min Act: -0.1700
Data Index: 5932872 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.5181. Min Act: -0.1700
Data Index: 1332650 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.4869. Min Act: -0.1700
Data Index: 518889 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.5181. Min Act: -0.1700
Data Index: 5271302 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.4869. Min Act: -0.1700
Data Index: 4876702 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.4869. Min Act: -0.1700
Data Index: 5491157 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.4556. Min Act: -0.1700
Data Index: 7761562 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.4869. Min Act: -0.1700
Data Index: 3197233 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.4869. Min Act: -0.1700
Data Index: 5290481 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.4556. Min Act: -0.1700
Data Index: 4560857 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.4244. Min Act: -0.1700
Data Index: 7316826 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.3619. Min Act: -0.1700
Data Index: 8456408 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.3931. Min Act: -0.1700
Data Index: 982812 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.3619. Min Act: -0.1700
Data Index: 2383465 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.3619. Min Act: -0.1700
Data Index: 1050075 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.3619. Min Act: -0.1700
Data Index: 1123870 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8306. Min Range: -5.8306
Max Act: 5.3619. Min Act: -0.1700
Data Index: 8196153 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19