Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.8106. Min Act: -0.1700
Data Index: 5802996 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.7480. Min Act: -0.1700
Data Index: 5283335 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.7167. Min Act: -0.1700
Data Index: 5967927 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.7324. Min Act: -0.1700
Data Index: 5283331 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.7324. Min Act: -0.1700
Data Index: 5283334 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.6698. Min Act: -0.1700
Data Index: 5283332 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.6698. Min Act: -0.1700
Data Index: 4910052 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.6229. Min Act: -0.1700
Data Index: 6333638 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.6229. Min Act: -0.1700
Data Index: 5818874 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.6072. Min Act: -0.1700
Data Index: 2912147 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5759. Min Act: -0.1700
Data Index: 8110697 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5759. Min Act: -0.1700
Data Index: 2325189 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5603. Min Act: -0.1700
Data Index: 8067677 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5603. Min Act: -0.1700
Data Index: 3624831 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5603. Min Act: -0.1700
Data Index: 6685578 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5603. Min Act: -0.1700
Data Index: 5031604 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5446. Min Act: -0.1700
Data Index: 8225951 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5289. Min Act: -0.1700
Data Index: 14105 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5133. Min Act: -0.1700
Data Index: 4950225 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8106. Min Range: -3.8106
Max Act: 3.5133. Min Act: -0.1700
Data Index: 6202109 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19