Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1159 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.1717. Min Act: -0.1700
Data Index: 4963719 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.1402. Min Act: -0.1700
Data Index: 3372807 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.1087. Min Act: -0.1700
Data Index: 408921 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.1245. Min Act: -0.1700
Data Index: 5237679 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.1087. Min Act: -0.1700
Data Index: 7214466 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.1087. Min Act: -0.1700
Data Index: 6185086 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0772. Min Act: -0.1700
Data Index: 2077156 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0456. Min Act: -0.1700
Data Index: 2348905 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0614. Min Act: -0.1700
Data Index: 1448497 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0614. Min Act: -0.1700
Data Index: 2880230 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0614. Min Act: -0.1700
Data Index: 8545099 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0299. Min Act: -0.1700
Data Index: 3000110 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0299. Min Act: -0.1700
Data Index: 6846689 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9983. Min Act: -0.1700
Data Index: 6029671 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0141. Min Act: -0.1700
Data Index: 886702 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0299. Min Act: -0.1700
Data Index: 3478387 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0456. Min Act: -0.1700
Data Index: 1712346 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9983. Min Act: -0.1700
Data Index: 5748192 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1717. Min Range: -3.1717
Max Act: 3.0141. Min Act: -0.1700
Data Index: 2601579 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1717. Min Range: -3.1717
Max Act: 2.9983. Min Act: -0.1700
Data Index: 1893339 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19