Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 358 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.3763. Min Act: -0.1700
Data Index: 8086523 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.2201. Min Act: -0.1700
Data Index: 22919 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.1263. Min Act: -0.1700
Data Index: 6134160 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.1263. Min Act: -0.1700
Data Index: 8313317 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.0951. Min Act: -0.1700
Data Index: 6305571 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.0326. Min Act: -0.1700
Data Index: 125563 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.0638. Min Act: -0.1700
Data Index: 8617720 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.0638. Min Act: -0.1700
Data Index: 6762917 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.0013. Min Act: -0.1700
Data Index: 7979492 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.0326. Min Act: -0.1700
Data Index: 4345025 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.0013. Min Act: -0.1700
Data Index: 8693428 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3763. Min Range: -5.3763
Max Act: 5.0013. Min Act: -0.1700
Data Index: 3128006 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3763. Min Range: -5.3763
Max Act: 4.9701. Min Act: -0.1700
Data Index: 6234185 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3763. Min Range: -5.3763
Max Act: 4.9701. Min Act: -0.1700
Data Index: 7501159 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3763. Min Range: -5.3763
Max Act: 4.9701. Min Act: -0.1700
Data Index: 4181266 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3763. Min Range: -5.3763
Max Act: 4.9701. Min Act: -0.1700
Data Index: 8021380 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3763. Min Range: -5.3763
Max Act: 4.9701. Min Act: -0.1700
Data Index: 7501161 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3763. Min Range: -5.3763
Max Act: 4.9388. Min Act: -0.1700
Data Index: 4385061 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3763. Min Range: -5.3763
Max Act: 4.9388. Min Act: -0.1700
Data Index: 4468653 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3763. Min Range: -5.3763
Max Act: 4.9076. Min Act: -0.1700
Data Index: 4464634 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19