Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3690 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.6090. Min Act: -0.1700
Data Index: 2991447 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.6090. Min Act: -0.1700
Data Index: 6804488 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.6090. Min Act: -0.1700
Data Index: 4234318 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.5152. Min Act: -0.1700
Data Index: 4083121 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.5465. Min Act: -0.1700
Data Index: 7054081 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.4840. Min Act: -0.1700
Data Index: 7205774 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.4527. Min Act: -0.1700
Data Index: 4336507 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.4215. Min Act: -0.1700
Data Index: 8290078 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.4215. Min Act: -0.1700
Data Index: 4096959 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.4215. Min Act: -0.1700
Data Index: 5579110 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3902. Min Act: -0.1700
Data Index: 995186 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3902. Min Act: -0.1700
Data Index: 4728203 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3590. Min Act: -0.1700
Data Index: 7572088 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3590. Min Act: -0.1700
Data Index: 7505128 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3590. Min Act: -0.1700
Data Index: 7344522 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3590. Min Act: -0.1700
Data Index: 1246178 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3590. Min Act: -0.1700
Data Index: 2717162 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3590. Min Act: -0.1700
Data Index: 482809 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3277. Min Act: -0.1700
Data Index: 4389881 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6090. Min Range: -4.6090
Max Act: 4.3277. Min Act: -0.1700
Data Index: 4329187 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19