Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2318. Min Range: -6.2318
Max Act: 6.2318. Min Act: -0.1700
Data Index: 2847885 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.9505. Min Act: -0.1700
Data Index: 7350858 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.9505. Min Act: -0.1700
Data Index: 2298253 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.8255. Min Act: -0.1700
Data Index: 6068268 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.7630. Min Act: -0.1700
Data Index: 7350855 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.7630. Min Act: -0.1700
Data Index: 4454313 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.7630. Min Act: -0.1700
Data Index: 2111868 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.7630. Min Act: -0.1700
Data Index: 4280966 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.7005. Min Act: -0.1700
Data Index: 4262374 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.7318. Min Act: -0.1700
Data Index: 7350856 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6693. Min Act: -0.1700
Data Index: 8776413 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6693. Min Act: -0.1700
Data Index: 4400395 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6380. Min Act: -0.1700
Data Index: 1250398 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6380. Min Act: -0.1700
Data Index: 468662 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6380. Min Act: -0.1700
Data Index: 2649937 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6380. Min Act: -0.1700
Data Index: 7218392 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6068. Min Act: -0.1700
Data Index: 8234723 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6380. Min Act: -0.1700
Data Index: 6569536 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.6380. Min Act: -0.1700
Data Index: 2632900 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2318. Min Range: -6.2318
Max Act: 5.5755. Min Act: -0.1700
Data Index: 6651928 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19