Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8716. Min Act: -0.1700
Data Index: 524107 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8459. Min Act: -0.1700
Data Index: 6745786 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8373. Min Act: -0.1700
Data Index: 4836001 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8201. Min Act: -0.1700
Data Index: 1422613 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8459. Min Act: -0.1698
Data Index: 5947801 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8116. Min Act: -0.1700
Data Index: 6745999 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8116. Min Act: -0.1700
Data Index: 1965530 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8116. Min Act: -0.1700
Data Index: 4245540 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8030. Min Act: -0.1700
Data Index: 7412366 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.8116. Min Act: -0.1700
Data Index: 1772463 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7857. Min Act: -0.1700
Data Index: 6411577 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7944. Min Act: -0.1700
Data Index: 1635719 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7857. Min Act: -0.1700
Data Index: 163388 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7857. Min Act: -0.1700
Data Index: 7273120 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7857. Min Act: -0.1700
Data Index: 3089823 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7857. Min Act: -0.1700
Data Index: 2928395 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7857. Min Act: -0.1700
Data Index: 6922096 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7512. Min Act: -0.1700
Data Index: 5872276 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7426. Min Act: -0.1700
Data Index: 7078480 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8716. Min Range: -1.8716
Max Act: 1.7599. Min Act: -0.1697
Data Index: 4185545 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19