Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.5075. Min Act: -0.1700
Data Index: 1963636 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.3513. Min Act: -0.1700
Data Index: 1621975 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.3200. Min Act: -0.1700
Data Index: 6481219 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2888. Min Act: -0.1700
Data Index: 538818 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2888. Min Act: -0.1700
Data Index: 7105722 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2888. Min Act: -0.1700
Data Index: 573085 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2263. Min Act: -0.1700
Data Index: 1935313 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2888. Min Act: -0.1700
Data Index: 914372 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2575. Min Act: -0.1700
Data Index: 3597199 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2575. Min Act: -0.1700
Data Index: 3651336 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.1950. Min Act: -0.1700
Data Index: 1641209 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2263. Min Act: -0.1700
Data Index: 1866407 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2263. Min Act: -0.1700
Data Index: 6007977 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2263. Min Act: -0.1700
Data Index: 4447632 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2263. Min Act: -0.1700
Data Index: 931024 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2263. Min Act: -0.1700
Data Index: 7645050 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2263. Min Act: -0.1700
Data Index: 633489 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.2263. Min Act: -0.1700
Data Index: 5410402 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.1950. Min Act: -0.1700
Data Index: 1427177 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5075. Min Range: -4.5075
Max Act: 4.1950. Min Act: -0.1700
Data Index: 2643617 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19