Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0403. Min Range: -5.0403
Max Act: 5.0403. Min Act: -0.1700
Data Index: 1347689 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.9778. Min Act: -0.1700
Data Index: 2582811 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.8840. Min Act: -0.1700
Data Index: 829756 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.8840. Min Act: -0.1700
Data Index: 829754 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.8840. Min Act: -0.1700
Data Index: 4224826 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.8528. Min Act: -0.1700
Data Index: 8013720 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.8215. Min Act: -0.1700
Data Index: 1601911 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.7590. Min Act: -0.1700
Data Index: 8368468 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6965. Min Act: -0.1700
Data Index: 2331488 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6653. Min Act: -0.1700
Data Index: 1780681 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6653. Min Act: -0.1700
Data Index: 5842454 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6653. Min Act: -0.1700
Data Index: 5109263 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6653. Min Act: -0.1700
Data Index: 1785617 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6653. Min Act: -0.1700
Data Index: 829755 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6340. Min Act: -0.1700
Data Index: 8785553 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6340. Min Act: -0.1700
Data Index: 7802543 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6340. Min Act: -0.1700
Data Index: 1707879 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6340. Min Act: -0.1700
Data Index: 7965252 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6340. Min Act: -0.1700
Data Index: 6558005 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0403. Min Range: -5.0403
Max Act: 4.6028. Min Act: -0.1700
Data Index: 4658845 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19