Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1888 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.4071. Min Act: -0.1700
Data Index: 1718371 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.4071. Min Act: -0.1700
Data Index: 7430261 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.2821. Min Act: -0.1700
Data Index: 7170791 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.2196. Min Act: -0.1700
Data Index: 1303959 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.1571. Min Act: -0.1700
Data Index: 8352095 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.1883. Min Act: -0.1700
Data Index: 6857222 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0633. Min Act: -0.1700
Data Index: 7093492 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0321. Min Act: -0.1700
Data Index: 4387098 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0321. Min Act: -0.1700
Data Index: 6170906 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0321. Min Act: -0.1700
Data Index: 4780632 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0321. Min Act: -0.1700
Data Index: 6922846 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4071. Min Range: -4.4071
Max Act: 3.9852. Min Act: -0.1700
Data Index: 5977560 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0008. Min Act: -0.1700
Data Index: 1863661 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4071. Min Range: -4.4071
Max Act: 3.9852. Min Act: -0.1700
Data Index: 5206827 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0008. Min Act: -0.1700
Data Index: 8503746 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0008. Min Act: -0.1700
Data Index: 6236001 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4071. Min Range: -4.4071
Max Act: 3.9852. Min Act: -0.1700
Data Index: 7862585 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4071. Min Range: -4.4071
Max Act: 3.9539. Min Act: -0.1700
Data Index: 565199 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4071. Min Range: -4.4071
Max Act: 3.9852. Min Act: -0.1700
Data Index: 2137641 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4071. Min Range: -4.4071
Max Act: 4.0008. Min Act: -0.1700
Data Index: 384506 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19