Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.2278. Min Act: -0.1700
Data Index: 472543 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1966. Min Act: -0.1700
Data Index: 1147803 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.2278. Min Act: -0.1700
Data Index: 2252213 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1341. Min Act: -0.1700
Data Index: 2151707 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1341. Min Act: -0.1700
Data Index: 1958495 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1341. Min Act: -0.1700
Data Index: 5831182 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1341. Min Act: -0.1700
Data Index: 4609095 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1341. Min Act: -0.1700
Data Index: 8107719 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1341. Min Act: -0.1700
Data Index: 6724495 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1028. Min Act: -0.1700
Data Index: 7504868 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1341. Min Act: -0.1700
Data Index: 53065 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1028. Min Act: -0.1700
Data Index: 961704 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1028. Min Act: -0.1700
Data Index: 6817066 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.0716. Min Act: -0.1700
Data Index: 5661606 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.1341. Min Act: -0.1700
Data Index: 6652915 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.0716. Min Act: -0.1700
Data Index: 6519918 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.0716. Min Act: -0.1700
Data Index: 1939712 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.0403. Min Act: -0.1700
Data Index: 415793 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.0403. Min Act: -0.1700
Data Index: 5744778 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2278. Min Range: -5.2278
Max Act: 5.0716. Min Act: -0.1700
Data Index: 1032362 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19