Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.7438. Min Act: -0.1696
Data Index: 6191357 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.7125. Min Act: -0.1699
Data Index: 6263763 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.4938. Min Act: -0.1698
Data Index: 7002789 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.5563. Min Act: -0.1695
Data Index: 97265 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.4313. Min Act: -0.1700
Data Index: 226720 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.4313. Min Act: -0.1697
Data Index: 7138318 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3688. Min Act: -0.1700
Data Index: 6026619 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3063. Min Act: -0.1692
Data Index: 1737540 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3375. Min Act: -0.1699
Data Index: 6941855 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3688. Min Act: -0.1700
Data Index: 5257041 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3063. Min Act: -0.1669
Data Index: 6301477 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3375. Min Act: -0.1700
Data Index: 5310982 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.2125. Min Act: -0.1700
Data Index: 7299999 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.2438. Min Act: -0.1700
Data Index: 8727996 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.2438. Min Act: -0.1699
Data Index: 5135932 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3688. Min Act: -0.1700
Data Index: 762521 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3063. Min Act: -0.1700
Data Index: 4251289 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.3063. Min Act: -0.1700
Data Index: 97264 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.2438. Min Act: -0.1700
Data Index: 2285047 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7438. Min Range: -5.7438
Max Act: 5.2125. Min Act: -0.1697
Data Index: 3107291 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19