Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4875 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0015. Min Range: -7.0015
Max Act: 7.0015. Min Act: -0.1700
Data Index: 1484379 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.9077. Min Act: -0.1700
Data Index: 8393054 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.8765. Min Act: -0.1700
Data Index: 1737159 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.8765. Min Act: -0.1700
Data Index: 1380633 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.8452. Min Act: -0.1700
Data Index: 1323642 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.8452. Min Act: -0.1700
Data Index: 1985999 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.7515. Min Act: -0.1700
Data Index: 1778439 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.7202. Min Act: -0.1700
Data Index: 4765140 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.6890. Min Act: -0.1700
Data Index: 5951135 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.7202. Min Act: -0.1700
Data Index: 581016 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.6890. Min Act: -0.1700
Data Index: 8621424 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.6890. Min Act: -0.1700
Data Index: 1261293 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.7202. Min Act: -0.1700
Data Index: 1261292 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.6265. Min Act: -0.1700
Data Index: 866568 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.6265. Min Act: -0.1700
Data Index: 6592874 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.6265. Min Act: -0.1700
Data Index: 8458426 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.5952. Min Act: -0.1700
Data Index: 6213538 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.5952. Min Act: -0.1700
Data Index: 5185332 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.5640. Min Act: -0.1700
Data Index: 3659859 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0015. Min Range: -7.0015
Max Act: 6.6265. Min Act: -0.1700
Data Index: 1382106 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19