Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1865 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0369. Min Range: -10.0369
Max Act: 10.0369. Min Act: -0.1700
Data Index: 7102742 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.9744. Min Act: -0.1700
Data Index: 6877175 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.9119. Min Act: -0.1700
Data Index: 6329575 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.9119. Min Act: -0.1698
Data Index: 7580957 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.8494. Min Act: -0.1700
Data Index: 322453 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.8494. Min Act: -0.1700
Data Index: 1366760 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.8494. Min Act: -0.1700
Data Index: 928273 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.7869. Min Act: -0.1700
Data Index: 5888491 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.7244. Min Act: -0.1700
Data Index: 1907764 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.7244. Min Act: -0.1700
Data Index: 3994339 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.6619. Min Act: -0.1700
Data Index: 5026962 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.6619. Min Act: -0.1700
Data Index: 5194560 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.5994. Min Act: -0.1700
Data Index: 4191176 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.5994. Min Act: -0.1700
Data Index: 1785330 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.5994. Min Act: -0.1700
Data Index: 4249259 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.5994. Min Act: -0.1700
Data Index: 4174507 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.5994. Min Act: -0.1700
Data Index: 8167148 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.5994. Min Act: -0.1700
Data Index: 2446259 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.5994. Min Act: -0.1700
Data Index: 589251 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0369. Min Range: -10.0369
Max Act: 9.5994. Min Act: -0.1700
Data Index: 6217778 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19