Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.4848. Min Act: -0.1700
Data Index: 8104221 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.5160. Min Act: -0.1700
Data Index: 5860129 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.4848. Min Act: -0.1700
Data Index: 1789827 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.4223. Min Act: -0.1700
Data Index: 670109 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.4223. Min Act: -0.1700
Data Index: 6277988 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3910. Min Act: -0.1700
Data Index: 6423538 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.4223. Min Act: -0.1700
Data Index: 8242426 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3910. Min Act: -0.1700
Data Index: 6480483 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3598. Min Act: -0.1700
Data Index: 1738447 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3910. Min Act: -0.1700
Data Index: 3904810 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.4223. Min Act: -0.1700
Data Index: 6786550 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3910. Min Act: -0.1700
Data Index: 6634775 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3910. Min Act: -0.1700
Data Index: 7778506 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3910. Min Act: -0.1700
Data Index: 3848258 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3910. Min Act: -0.1700
Data Index: 1577121 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.4223. Min Act: -0.1700
Data Index: 7851780 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3598. Min Act: -0.1700
Data Index: 2680982 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3598. Min Act: -0.1700
Data Index: 7088024 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3598. Min Act: -0.1700
Data Index: 1231231 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5160. Min Range: -4.5160
Max Act: 4.3285. Min Act: -0.1700
Data Index: 1861001 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19