Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3775 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.4960. Min Act: -0.1700
Data Index: 5934746 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.4022. Min Act: -0.1700
Data Index: 4648925 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.4022. Min Act: -0.1700
Data Index: 7601895 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.4022. Min Act: -0.1700
Data Index: 5181116 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3710. Min Act: -0.1700
Data Index: 2090303 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3710. Min Act: -0.1700
Data Index: 637110 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3710. Min Act: -0.1700
Data Index: 8059904 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3397. Min Act: -0.1700
Data Index: 5641913 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3397. Min Act: -0.1700
Data Index: 3622540 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3085. Min Act: -0.1700
Data Index: 4264449 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3085. Min Act: -0.1700
Data Index: 5071247 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3397. Min Act: -0.1700
Data Index: 7643163 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3085. Min Act: -0.1700
Data Index: 5500114 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.3085. Min Act: -0.1700
Data Index: 2065509 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.2772. Min Act: -0.1700
Data Index: 5081199 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.2460. Min Act: -0.1700
Data Index: 2791197 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.2460. Min Act: -0.1700
Data Index: 7603052 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.2460. Min Act: -0.1700
Data Index: 5579621 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.2460. Min Act: -0.1700
Data Index: 3834868 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4960. Min Range: -5.4960
Max Act: 5.2147. Min Act: -0.1700
Data Index: 3670431 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19