Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 517 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.6732. Min Act: -0.1700
Data Index: 6957138 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.6419. Min Act: -0.1700
Data Index: 4923996 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.6107. Min Act: -0.1700
Data Index: 4862852 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5794. Min Act: -0.1700
Data Index: 4300080 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5482. Min Act: -0.1700
Data Index: 769516 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5482. Min Act: -0.1700
Data Index: 2765724 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5794. Min Act: -0.1700
Data Index: 8344111 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5482. Min Act: -0.1700
Data Index: 1577962 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5482. Min Act: -0.1700
Data Index: 8541936 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5169. Min Act: -0.1700
Data Index: 8367578 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5169. Min Act: -0.1700
Data Index: 1783665 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4857. Min Act: -0.1700
Data Index: 5488 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5169. Min Act: -0.1700
Data Index: 3843404 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4857. Min Act: -0.1700
Data Index: 5381485 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4857. Min Act: -0.1700
Data Index: 3342078 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.5169. Min Act: -0.1700
Data Index: 3246842 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4544. Min Act: -0.1700
Data Index: 5816744 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4857. Min Act: -0.1700
Data Index: 6114773 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4544. Min Act: -0.1700
Data Index: 7790901 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6732. Min Range: -4.6732
Max Act: 4.4857. Min Act: -0.1700
Data Index: 8197467 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19