Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4894. Min Act: -0.1700
Data Index: 3086611 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4894. Min Act: -0.1700
Data Index: 2895123 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4894. Min Act: -0.1700
Data Index: 2464189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4894. Min Act: -0.1700
Data Index: 8477818 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 3975342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 2873353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4269. Min Act: -0.1700
Data Index: 2610712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 476389 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 8672699 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 7652509 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 931326 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 7206500 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4269. Min Act: -0.1700
Data Index: 7037473 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 5774906 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 5591629 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 5350778 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4581. Min Act: -0.1700
Data Index: 4291011 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4269. Min Act: -0.1700
Data Index: 3583474 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4269. Min Act: -0.1700
Data Index: 1047675 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4269. Min Act: -0.1700
Data Index: 3193177 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19