Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.8397. Min Act: -0.1700
Data Index: 1647834 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.8139. Min Act: -0.1700
Data Index: 3060968 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7795. Min Act: -0.1698
Data Index: 3970287 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7795. Min Act: -0.1700
Data Index: 427820 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7709. Min Act: -0.1700
Data Index: 8632852 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7709. Min Act: -0.1700
Data Index: 2686972 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7450. Min Act: -0.1699
Data Index: 4861254 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7191. Min Act: -0.1700
Data Index: 2974272 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7277. Min Act: -0.1700
Data Index: 7119831 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7191. Min Act: -0.1700
Data Index: 4748171 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7277. Min Act: -0.1700
Data Index: 3658644 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7277. Min Act: -0.1700
Data Index: 5560983 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7104. Min Act: -0.1700
Data Index: 4294408 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7104. Min Act: -0.1700
Data Index: 1506769 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7104. Min Act: -0.1700
Data Index: 7670804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.6931. Min Act: -0.1700
Data Index: 7566101 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7104. Min Act: -0.1700
Data Index: 2646021 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7017. Min Act: -0.1700
Data Index: 5011743 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.7104. Min Act: -0.1700
Data Index: 4530533 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8397. Min Range: -1.8397
Max Act: 1.6844. Min Act: -0.1700
Data Index: 2984946 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19