Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4502 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.9022. Min Act: -0.1700
Data Index: 2824430 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.7458. Min Act: -0.1700
Data Index: 1596369 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6989. Min Act: -0.1700
Data Index: 4269568 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6833. Min Act: -0.1700
Data Index: 2264611 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6833. Min Act: -0.1700
Data Index: 7374158 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6520. Min Act: -0.1700
Data Index: 2507934 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6207. Min Act: -0.1700
Data Index: 5701135 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6207. Min Act: -0.1700
Data Index: 346306 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6520. Min Act: -0.1700
Data Index: 1141644 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6363. Min Act: -0.1700
Data Index: 8747888 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6050. Min Act: -0.1700
Data Index: 3873695 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6050. Min Act: -0.1700
Data Index: 303571 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6050. Min Act: -0.1700
Data Index: 116575 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6207. Min Act: -0.1700
Data Index: 5585447 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.6050. Min Act: -0.1700
Data Index: 2446291 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.5894. Min Act: -0.1700
Data Index: 1030594 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.5581. Min Act: -0.1700
Data Index: 7361378 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.5737. Min Act: -0.1700
Data Index: 2751832 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.5581. Min Act: -0.1700
Data Index: 6713427 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9022. Min Range: -3.9022
Max Act: 3.5581. Min Act: -0.1700
Data Index: 1921444 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19