Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1685 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0703. Min Act: -0.1700
Data Index: 1440323 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0703. Min Act: -0.1700
Data Index: 4018739 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 1856686 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0390. Min Act: -0.1700
Data Index: 6827003 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 649581 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0703. Min Range: -5.0703
Max Act: 5.0078. Min Act: -0.1700
Data Index: 8112907 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9765. Min Act: -0.1700
Data Index: 5858020 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9765. Min Act: -0.1700
Data Index: 242240 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9765. Min Act: -0.1700
Data Index: 745299 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9765. Min Act: -0.1700
Data Index: 614345 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9765. Min Act: -0.1700
Data Index: 2357393 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9453. Min Act: -0.1700
Data Index: 583027 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9453. Min Act: -0.1700
Data Index: 258301 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9140. Min Act: -0.1700
Data Index: 4317574 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.9453. Min Act: -0.1700
Data Index: 4264920 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 5159257 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 6014231 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 7161529 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 8086891 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0703. Min Range: -5.0703
Max Act: 4.8828. Min Act: -0.1700
Data Index: 3282174 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19