Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3880 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.7236. Min Act: -0.1700
Data Index: 829213 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.2548. Min Act: -0.1700
Data Index: 3510198 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.1923. Min Act: -0.1700
Data Index: 1857326 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.1923. Min Act: -0.1700
Data Index: 8184039 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.1298. Min Act: -0.1700
Data Index: 920230 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.1298. Min Act: -0.1700
Data Index: 3143072 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.1298. Min Act: -0.1700
Data Index: 5510018 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0986. Min Act: -0.1700
Data Index: 5838737 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0673. Min Act: -0.1700
Data Index: 3602089 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0673. Min Act: -0.1700
Data Index: 2299405 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0673. Min Act: -0.1700
Data Index: 3337079 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0361. Min Act: -0.1700
Data Index: 1505064 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0361. Min Act: -0.1700
Data Index: 6942489 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0361. Min Act: -0.1700
Data Index: 2732053 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0361. Min Act: -0.1700
Data Index: 3674160 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0048. Min Act: -0.1700
Data Index: 4824641 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0048. Min Act: -0.1700
Data Index: 2448872 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7236. Min Range: -5.7236
Max Act: 5.0048. Min Act: -0.1700
Data Index: 3208095 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7236. Min Range: -5.7236
Max Act: 4.9736. Min Act: -0.1700
Data Index: 2299406 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7236. Min Range: -5.7236
Max Act: 4.9736. Min Act: -0.1700
Data Index: 2852371 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19