Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2673. Min Range: -6.2673
Max Act: 6.2673. Min Act: -0.1700
Data Index: 8019065 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2673. Min Range: -6.2673
Max Act: 6.2048. Min Act: -0.1700
Data Index: 4689321 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.9548. Min Act: -0.1700
Data Index: 7808076 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.9548. Min Act: -0.1700
Data Index: 2399007 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.8923. Min Act: -0.1700
Data Index: 8546419 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.8923. Min Act: -0.1700
Data Index: 4554441 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.8610. Min Act: -0.1700
Data Index: 5444689 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.8298. Min Act: -0.1700
Data Index: 5097136 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7985. Min Act: -0.1700
Data Index: 1641366 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7673. Min Act: -0.1700
Data Index: 4253927 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7673. Min Act: -0.1700
Data Index: 4890443 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7360. Min Act: -0.1700
Data Index: 3474985 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7360. Min Act: -0.1700
Data Index: 5270256 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7048. Min Act: -0.1700
Data Index: 447839 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7360. Min Act: -0.1700
Data Index: 6152065 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7048. Min Act: -0.1700
Data Index: 5449474 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.7048. Min Act: -0.1700
Data Index: 8717798 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.6735. Min Act: -0.1700
Data Index: 6435595 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.6423. Min Act: -0.1700
Data Index: 146692 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2673. Min Range: -6.2673
Max Act: 5.6735. Min Act: -0.1700
Data Index: 898382 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19