Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.6173. Min Act: -0.1700
Data Index: 958453 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.5236. Min Act: -0.1700
Data Index: 3087562 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.5236. Min Act: -0.1700
Data Index: 6360386 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.4923. Min Act: -0.1700
Data Index: 8768031 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.4923. Min Act: -0.1700
Data Index: 4813447 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.4923. Min Act: -0.1700
Data Index: 8295523 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.4298. Min Act: -0.1700
Data Index: 4960601 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.4611. Min Act: -0.1700
Data Index: 5879901 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3985. Min Act: -0.1700
Data Index: 6334221 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3985. Min Act: -0.1700
Data Index: 340974 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3985. Min Act: -0.1700
Data Index: 7576977 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3985. Min Act: -0.1700
Data Index: 4369981 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3673. Min Act: -0.1700
Data Index: 7770289 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3673. Min Act: -0.1700
Data Index: 8608863 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3673. Min Act: -0.1700
Data Index: 6931088 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3360. Min Act: -0.1700
Data Index: 369553 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3360. Min Act: -0.1700
Data Index: 351474 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3048. Min Act: -0.1700
Data Index: 2348417 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3048. Min Act: -0.1700
Data Index: 681222 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6173. Min Range: -4.6173
Max Act: 4.3048. Min Act: -0.1700
Data Index: 1421321 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19