Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 496 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1020. Min Range: -5.1020
Max Act: 5.1020. Min Act: -0.1700
Data Index: 6627234 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1020. Min Range: -5.1020
Max Act: 5.0083. Min Act: -0.1700
Data Index: 791330 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.9458. Min Act: -0.1700
Data Index: 3934083 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.9145. Min Act: -0.1700
Data Index: 1348435 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.9145. Min Act: -0.1700
Data Index: 8699129 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.8833. Min Act: -0.1700
Data Index: 3780754 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.8208. Min Act: -0.1700
Data Index: 4090028 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.8520. Min Act: -0.1700
Data Index: 8181065 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.7583. Min Act: -0.1700
Data Index: 1838899 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.7583. Min Act: -0.1700
Data Index: 7567379 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.7270. Min Act: -0.1700
Data Index: 8541859 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.7270. Min Act: -0.1700
Data Index: 4471187 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.7270. Min Act: -0.1700
Data Index: 704022 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.6958. Min Act: -0.1700
Data Index: 6083967 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.7270. Min Act: -0.1700
Data Index: 3387741 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.6958. Min Act: -0.1700
Data Index: 4036848 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.6958. Min Act: -0.1700
Data Index: 7949355 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.6958. Min Act: -0.1700
Data Index: 4128695 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.6645. Min Act: -0.1700
Data Index: 7218777 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1020. Min Range: -5.1020
Max Act: 4.6333. Min Act: -0.1700
Data Index: 2457334 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19