Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5287 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.4210. Min Act: -0.1700
Data Index: 6049215 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.2648. Min Act: -0.1700
Data Index: 3929325 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.2023. Min Act: -0.1700
Data Index: 2599539 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.2335. Min Act: -0.1700
Data Index: 5421946 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.2023. Min Act: -0.1700
Data Index: 4942023 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.1710. Min Act: -0.1699
Data Index: 8318568 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.2023. Min Act: -0.1700
Data Index: 206372 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.1710. Min Act: -0.1700
Data Index: 1793445 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.1710. Min Act: -0.1700
Data Index: 6970155 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.1085. Min Act: -0.1700
Data Index: 284901 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.1085. Min Act: -0.1700
Data Index: 7496991 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.1085. Min Act: -0.1700
Data Index: 8258274 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.0773. Min Act: -0.1700
Data Index: 6906727 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.1085. Min Act: -0.1700
Data Index: 5212116 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.0773. Min Act: -0.1700
Data Index: 3770668 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.0773. Min Act: -0.1700
Data Index: 642553 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.0773. Min Act: -0.1700
Data Index: 5128553 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.0773. Min Act: -0.1700
Data Index: 6542818 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.0460. Min Act: -0.1700
Data Index: 3321729 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4210. Min Range: -5.4210
Max Act: 5.0460. Min Act: -0.1700
Data Index: 2650766 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19