Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.5544. Min Act: -0.1687
Data Index: 5001870 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.5281. Min Act: -0.1700
Data Index: 2023461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.5281. Min Act: -0.1697
Data Index: 7711008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.5106. Min Act: -0.1700
Data Index: 5989601 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.5018. Min Act: -0.1695
Data Index: 2779230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.5018. Min Act: -0.1700
Data Index: 7607214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4666. Min Act: -0.1698
Data Index: 6090791 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4754. Min Act: -0.1674
Data Index: 8812536 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4403. Min Act: -0.1688
Data Index: 667061 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4403. Min Act: -0.1700
Data Index: 7474591 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4403. Min Act: -0.1700
Data Index: 5021533 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4314. Min Act: -0.1700
Data Index: 5754151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4314. Min Act: -0.1700
Data Index: 7188061 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4314. Min Act: -0.1699
Data Index: 6852324 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4314. Min Act: -0.1700
Data Index: 4340359 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4314. Min Act: -0.1699
Data Index: 5321380 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4226. Min Act: -0.1695
Data Index: 3158499 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4138. Min Act: -0.1699
Data Index: 935817 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4226. Min Act: -0.1696
Data Index: 2668361 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5544. Min Range: -1.5544
Max Act: 1.4314. Min Act: -0.1696
Data Index: 992449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19