Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0114. Min Range: -6.0114
Max Act: 6.0114. Min Act: -0.1700
Data Index: 5457308 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.9489. Min Act: -0.1700
Data Index: 5064901 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.8239. Min Act: -0.1700
Data Index: 3348470 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.8239. Min Act: -0.1700
Data Index: 2399383 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.7614. Min Act: -0.1700
Data Index: 3110282 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.7302. Min Act: -0.1700
Data Index: 3913356 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.6989. Min Act: -0.1700
Data Index: 4078813 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.6364. Min Act: -0.1700
Data Index: 2278279 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.5739. Min Act: -0.1700
Data Index: 8795992 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.6052. Min Act: -0.1700
Data Index: 2733635 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.6052. Min Act: -0.1700
Data Index: 4282228 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.5739. Min Act: -0.1700
Data Index: 5836990 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.5739. Min Act: -0.1700
Data Index: 1824579 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.5739. Min Act: -0.1700
Data Index: 4888981 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.5739. Min Act: -0.1700
Data Index: 7911599 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.5114. Min Act: -0.1700
Data Index: 1733203 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.5114. Min Act: -0.1700
Data Index: 5785566 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.4489. Min Act: -0.1700
Data Index: 4537799 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.4489. Min Act: -0.1700
Data Index: 5354766 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0114. Min Range: -6.0114
Max Act: 5.4489. Min Act: -0.1700
Data Index: 3120500 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19