Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.1480. Min Act: -0.1700
Data Index: 2501119 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0603. Min Act: -0.1700
Data Index: 5588322 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0603. Min Act: -0.1700
Data Index: 7996176 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0603. Min Act: -0.1700
Data Index: 3773470 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0255. Min Act: -0.1700
Data Index: 8698665 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0255. Min Act: -0.1700
Data Index: 2674119 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0255. Min Act: -0.1700
Data Index: 7346560 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0081. Min Act: -0.1700
Data Index: 3024735 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9907. Min Act: -0.1700
Data Index: 8571239 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0081. Min Act: -0.1700
Data Index: 6847404 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1480. Min Range: -1.1480
Max Act: 1.0081. Min Act: -0.1700
Data Index: 757570 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9907. Min Act: -0.1700
Data Index: 506355 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9907. Min Act: -0.1700
Data Index: 3380686 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9907. Min Act: -0.1700
Data Index: 6213950 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9907. Min Act: -0.1700
Data Index: 419036 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9907. Min Act: -0.1700
Data Index: 2222512 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9907. Min Act: -0.1700
Data Index: 4799428 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9907. Min Act: -0.1700
Data Index: 3397120 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9734. Min Act: -0.1700
Data Index: 79612 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1480. Min Range: -1.1480
Max Act: 0.9734. Min Act: -0.1700
Data Index: 5639137 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19