Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 935 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0580. Min Range: -5.0580
Max Act: 5.0580. Min Act: -0.1700
Data Index: 8357449 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0580. Min Range: -5.0580
Max Act: 5.0580. Min Act: -0.1700
Data Index: 8113165 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0580. Min Range: -5.0580
Max Act: 5.0268. Min Act: -0.1700
Data Index: 6413292 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0580. Min Range: -5.0580
Max Act: 5.0268. Min Act: -0.1700
Data Index: 3260384 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0580. Min Range: -5.0580
Max Act: 5.0268. Min Act: -0.1700
Data Index: 1596777 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 6778242 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 422689 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 644862 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 7777923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 7063569 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 6993486 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 4331509 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 3027825 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 2964243 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9643. Min Act: -0.1700
Data Index: 2933645 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 777728 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0580. Min Range: -5.0580
Max Act: 5.0268. Min Act: -0.1700
Data Index: 5883250 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 5600429 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 5448701 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0580. Min Range: -5.0580
Max Act: 4.9955. Min Act: -0.1700
Data Index: 2875507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19