Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.4923. Min Act: -0.1700
Data Index: 4355319 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.3048. Min Act: -0.1700
Data Index: 832004 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.2423. Min Act: -0.1700
Data Index: 4248119 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.1798. Min Act: -0.1700
Data Index: 4106275 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.2111. Min Act: -0.1700
Data Index: 3520348 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.1798. Min Act: -0.1700
Data Index: 3369443 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.1486. Min Act: -0.1700
Data Index: 3582087 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.1486. Min Act: -0.1700
Data Index: 2528972 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.0861. Min Act: -0.1700
Data Index: 404224 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.0548. Min Act: -0.1700
Data Index: 3520353 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.0548. Min Act: -0.1700
Data Index: 791209 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4923. Min Range: -5.4923
Max Act: 5.0236. Min Act: -0.1700
Data Index: 7517651 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4923. Min Range: -5.4923
Max Act: 4.9923. Min Act: -0.1700
Data Index: 1803442 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4923. Min Range: -5.4923
Max Act: 4.9923. Min Act: -0.1700
Data Index: 7241552 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4923. Min Range: -5.4923
Max Act: 4.9923. Min Act: -0.1700
Data Index: 6736400 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4923. Min Range: -5.4923
Max Act: 4.9923. Min Act: -0.1700
Data Index: 5600591 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4923. Min Range: -5.4923
Max Act: 4.9611. Min Act: -0.1700
Data Index: 6418008 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4923. Min Range: -5.4923
Max Act: 4.9611. Min Act: -0.1700
Data Index: 10685 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4923. Min Range: -5.4923
Max Act: 4.9611. Min Act: -0.1700
Data Index: 5730234 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4923. Min Range: -5.4923
Max Act: 4.9611. Min Act: -0.1700
Data Index: 884647 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19