Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1066 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.6251. Min Act: -0.1700
Data Index: 7549330 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.5001. Min Act: -0.1700
Data Index: 8016040 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.3751. Min Act: -0.1700
Data Index: 6598884 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.3126. Min Act: -0.1700
Data Index: 1961072 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2814. Min Act: -0.1700
Data Index: 6677133 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2814. Min Act: -0.1700
Data Index: 435388 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2814. Min Act: -0.1700
Data Index: 8094584 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2501. Min Act: -0.1700
Data Index: 7292957 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2501. Min Act: -0.1700
Data Index: 400909 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2501. Min Act: -0.1700
Data Index: 8674593 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2501. Min Act: -0.1700
Data Index: 1245190 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2501. Min Act: -0.1700
Data Index: 8674579 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2189. Min Act: -0.1700
Data Index: 6116849 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2189. Min Act: -0.1700
Data Index: 6327795 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.1876. Min Act: -0.1700
Data Index: 4795176 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.1876. Min Act: -0.1700
Data Index: 3729114 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.1876. Min Act: -0.1700
Data Index: 7274099 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.2189. Min Act: -0.1700
Data Index: 7292942 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.1564. Min Act: -0.1700
Data Index: 7332230 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6251. Min Range: -5.6251
Max Act: 5.1876. Min Act: -0.1700
Data Index: 1546268 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19