Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1067 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.9363. Min Act: -0.1700
Data Index: 4436160 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.8738. Min Act: -0.1700
Data Index: 6820755 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.8425. Min Act: -0.1700
Data Index: 4436162 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.8113. Min Act: -0.1700
Data Index: 1369815 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.8113. Min Act: -0.1700
Data Index: 3343499 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.7800. Min Act: -0.1700
Data Index: 6260159 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.8113. Min Act: -0.1700
Data Index: 210442 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.7800. Min Act: -0.1700
Data Index: 8115342 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.7175. Min Act: -0.1700
Data Index: 1226553 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.7175. Min Act: -0.1700
Data Index: 6249480 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.7175. Min Act: -0.1700
Data Index: 6483246 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.7175. Min Act: -0.1700
Data Index: 8384025 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.6862. Min Act: -0.1700
Data Index: 7271093 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.6550. Min Act: -0.1700
Data Index: 2029393 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.6862. Min Act: -0.1700
Data Index: 1135401 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.6550. Min Act: -0.1700
Data Index: 5186742 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.6550. Min Act: -0.1700
Data Index: 6106410 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.6550. Min Act: -0.1700
Data Index: 7029425 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.6237. Min Act: -0.1700
Data Index: 1388247 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9363. Min Range: -4.9363
Max Act: 4.6550. Min Act: -0.1700
Data Index: 4371537 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19