Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3273 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4655. Min Act: -0.1700
Data Index: 2507265 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4655. Min Act: -0.1700
Data Index: 7824196 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4342. Min Act: -0.1700
Data Index: 2961042 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4342. Min Act: -0.1700
Data Index: 4904106 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4342. Min Act: -0.1700
Data Index: 7735804 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 2006613 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 4931359 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 5554039 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 4362676 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 4056931 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 7171641 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 6398001 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 3111557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 6397997 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.4028. Min Act: -0.1700
Data Index: 2817525 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.3715. Min Act: -0.1700
Data Index: 105505 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.3715. Min Act: -0.1700
Data Index: 2215098 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.3715. Min Act: -0.1700
Data Index: 1085802 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.3715. Min Act: -0.1700
Data Index: 5157926 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4655. Min Range: -3.4655
Max Act: 3.3715. Min Act: -0.1700
Data Index: 5245064 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19