Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2532 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.5922. Min Act: -0.1700
Data Index: 8631632 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.3421. Min Act: -0.1700
Data Index: 814662 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.3109. Min Act: -0.1700
Data Index: 2800802 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.3109. Min Act: -0.1700
Data Index: 6424162 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.2796. Min Act: -0.1700
Data Index: 7877965 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.3109. Min Act: -0.1700
Data Index: 8719727 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.2796. Min Act: -0.1700
Data Index: 6174732 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.2484. Min Act: -0.1700
Data Index: 2999169 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.2484. Min Act: -0.1700
Data Index: 4040925 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.2171. Min Act: -0.1700
Data Index: 831845 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.2484. Min Act: -0.1700
Data Index: 7213183 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.1859. Min Act: -0.1700
Data Index: 3831258 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.2171. Min Act: -0.1700
Data Index: 8543757 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.1859. Min Act: -0.1700
Data Index: 1024339 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.1546. Min Act: -0.1700
Data Index: 814663 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.1234. Min Act: -0.1700
Data Index: 7309786 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.1234. Min Act: -0.1700
Data Index: 1054542 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.1546. Min Act: -0.1700
Data Index: 7118499 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.1546. Min Act: -0.1700
Data Index: 1072623 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5922. Min Range: -4.5922
Max Act: 4.1234. Min Act: -0.1700
Data Index: 4463074 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19