Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.7172. Min Act: -0.1700
Data Index: 4971286 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.5609. Min Act: -0.1700
Data Index: 1705403 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.5297. Min Act: -0.1700
Data Index: 3910578 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.4359. Min Act: -0.1700
Data Index: 73754 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.3734. Min Act: -0.1700
Data Index: 5000693 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.3422. Min Act: -0.1700
Data Index: 2146127 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.2484. Min Act: -0.1700
Data Index: 8044963 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.1859. Min Act: -0.1700
Data Index: 5938983 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.1859. Min Act: -0.1700
Data Index: 4951824 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.1547. Min Act: -0.1700
Data Index: 8557300 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.1547. Min Act: -0.1700
Data Index: 6750581 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.1234. Min Act: -0.1700
Data Index: 110737 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.1234. Min Act: -0.1700
Data Index: 575793 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.0922. Min Act: -0.1700
Data Index: 7091215 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.0922. Min Act: -0.1700
Data Index: 5268050 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.0609. Min Act: -0.1700
Data Index: 6339497 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.0297. Min Act: -0.1700
Data Index: 5100978 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.0297. Min Act: -0.1700
Data Index: 331248 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.0297. Min Act: -0.1700
Data Index: 6019736 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7172. Min Range: -5.7172
Max Act: 5.0609. Min Act: -0.1700
Data Index: 7430760 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19