Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.8903. Min Act: -0.1700
Data Index: 2307588 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.8278. Min Act: -0.1700
Data Index: 2463682 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.5778. Min Act: -0.1700
Data Index: 1415502 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.5153. Min Act: -0.1700
Data Index: 4541302 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.5153. Min Act: -0.1700
Data Index: 6571910 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.4528. Min Act: -0.1700
Data Index: 1287738 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.4528. Min Act: -0.1700
Data Index: 6944606 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.3903. Min Act: -0.1700
Data Index: 4720184 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.3278. Min Act: -0.1700
Data Index: 6383716 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.3903. Min Act: -0.1700
Data Index: 7091845 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.3278. Min Act: -0.1700
Data Index: 6893388 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.2653. Min Act: -0.1700
Data Index: 8200748 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.2653. Min Act: -0.1700
Data Index: 7812716 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.2653. Min Act: -0.1700
Data Index: 3457743 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.2653. Min Act: -0.1700
Data Index: 1048047 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.2653. Min Act: -0.1700
Data Index: 6004123 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.2028. Min Act: -0.1700
Data Index: 4432095 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.2028. Min Act: -0.1700
Data Index: 4824740 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.1403. Min Act: -0.1700
Data Index: 6528829 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8903. Min Range: -9.8903
Max Act: 9.1403. Min Act: -0.1700
Data Index: 4136087 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19