Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.5456. Min Act: -0.1700
Data Index: 1660823 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.5143. Min Act: -0.1700
Data Index: 6240463 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4830. Min Act: -0.1700
Data Index: 7543372 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4830. Min Act: -0.1700
Data Index: 4030856 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4516. Min Act: -0.1700
Data Index: 5810378 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4359. Min Act: -0.1700
Data Index: 7060582 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4830. Min Act: -0.1700
Data Index: 4968827 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4516. Min Act: -0.1700
Data Index: 2066861 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4673. Min Act: -0.1700
Data Index: 1979901 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4673. Min Act: -0.1700
Data Index: 2153320 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4203. Min Act: -0.1700
Data Index: 237102 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4516. Min Act: -0.1700
Data Index: 3466553 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4359. Min Act: -0.1700
Data Index: 4589777 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4203. Min Act: -0.1700
Data Index: 7161781 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4046. Min Act: -0.1700
Data Index: 2779201 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4203. Min Act: -0.1700
Data Index: 8223302 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.3889. Min Act: -0.1700
Data Index: 2536222 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4046. Min Act: -0.1700
Data Index: 4148281 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.3889. Min Act: -0.1700
Data Index: 3031402 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5456. Min Range: -3.5456
Max Act: 3.4516. Min Act: -0.1700
Data Index: 4315365 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19