Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4545 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0554. Min Range: -6.0554
Max Act: 6.0554. Min Act: -0.1700
Data Index: 1241120 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.9929. Min Act: -0.1700
Data Index: 1946509 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.9304. Min Act: -0.1700
Data Index: 574351 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.9304. Min Act: -0.1700
Data Index: 742547 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.8366. Min Act: -0.1700
Data Index: 3561509 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.8679. Min Act: -0.1700
Data Index: 8364794 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.8366. Min Act: -0.1700
Data Index: 3298345 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.8054. Min Act: -0.1700
Data Index: 5769032 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7741. Min Act: -0.1700
Data Index: 4451390 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7741. Min Act: -0.1700
Data Index: 3022140 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7741. Min Act: -0.1700
Data Index: 275893 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7741. Min Act: -0.1700
Data Index: 4635687 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7429. Min Act: -0.1700
Data Index: 6837220 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7429. Min Act: -0.1700
Data Index: 641645 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7429. Min Act: -0.1700
Data Index: 7051673 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7429. Min Act: -0.1700
Data Index: 7526030 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.7116. Min Act: -0.1700
Data Index: 6092194 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.6804. Min Act: -0.1700
Data Index: 1791722 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.6804. Min Act: -0.1700
Data Index: 2694191 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0554. Min Range: -6.0554
Max Act: 5.6804. Min Act: -0.1700
Data Index: 7566384 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19