Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1025 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0638. Min Range: -4.0638
Max Act: 4.0638. Min Act: -0.1700
Data Index: 8637796 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0638. Min Range: -4.0638
Max Act: 4.0638. Min Act: -0.1700
Data Index: 4528411 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0638. Min Range: -4.0638
Max Act: 4.0326. Min Act: -0.1700
Data Index: 5037962 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0638. Min Range: -4.0638
Max Act: 4.0326. Min Act: -0.1700
Data Index: 4278300 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9700. Min Act: -0.1700
Data Index: 2013106 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0638. Min Range: -4.0638
Max Act: 4.0013. Min Act: -0.1700
Data Index: 5253689 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9700. Min Act: -0.1700
Data Index: 4912080 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9700. Min Act: -0.1700
Data Index: 3721692 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9700. Min Act: -0.1700
Data Index: 2978208 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9388. Min Act: -0.1700
Data Index: 1884269 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9700. Min Act: -0.1700
Data Index: 2406008 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9700. Min Act: -0.1700
Data Index: 5321986 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9388. Min Act: -0.1700
Data Index: 4634106 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9388. Min Act: -0.1700
Data Index: 1170222 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9700. Min Act: -0.1700
Data Index: 3235147 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9700. Min Act: -0.1700
Data Index: 2332247 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9388. Min Act: -0.1700
Data Index: 3843647 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9388. Min Act: -0.1700
Data Index: 4494672 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9388. Min Act: -0.1700
Data Index: 1389641 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0638. Min Range: -4.0638
Max Act: 3.9075. Min Act: -0.1700
Data Index: 2157303 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19