Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1709 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2975. Min Range: -5.2975
Max Act: 5.2662. Min Act: -0.1700
Data Index: 8016375 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2975. Min Range: -5.2975
Max Act: 5.2975. Min Act: -0.1700
Data Index: 104149 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2975. Min Range: -5.2975
Max Act: 5.1412. Min Act: -0.1700
Data Index: 8419377 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2975. Min Range: -5.2975
Max Act: 5.1100. Min Act: -0.1700
Data Index: 1719238 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2975. Min Range: -5.2975
Max Act: 5.0475. Min Act: -0.1700
Data Index: 4232966 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.9850. Min Act: -0.1700
Data Index: 337191 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2975. Min Range: -5.2975
Max Act: 5.0475. Min Act: -0.1700
Data Index: 1371990 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2975. Min Range: -5.2975
Max Act: 5.0162. Min Act: -0.1700
Data Index: 5086874 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.9850. Min Act: -0.1700
Data Index: 6645560 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2975. Min Range: -5.2975
Max Act: 5.0162. Min Act: -0.1700
Data Index: 3642475 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.9537. Min Act: -0.1700
Data Index: 5268057 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.9537. Min Act: -0.1700
Data Index: 5685476 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.9225. Min Act: -0.1700
Data Index: 5947728 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.9225. Min Act: -0.1700
Data Index: 6812158 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.9225. Min Act: -0.1700
Data Index: 1178947 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.8912. Min Act: -0.1700
Data Index: 4018296 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.8600. Min Act: -0.1700
Data Index: 5379049 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.8912. Min Act: -0.1700
Data Index: 1450434 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.8912. Min Act: -0.1700
Data Index: 1259025 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2975. Min Range: -5.2975
Max Act: 4.8912. Min Act: -0.1700
Data Index: 3548447 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19