Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2675 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.8942. Min Act: -0.1700
Data Index: 8616022 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.8942. Min Act: -0.1700
Data Index: 452645 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.7692. Min Act: -0.1700
Data Index: 2486451 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.7692. Min Act: -0.1700
Data Index: 2931718 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.6754. Min Act: -0.1700
Data Index: 3187085 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.6754. Min Act: -0.1700
Data Index: 6111226 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.6129. Min Act: -0.1700
Data Index: 1545186 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.6129. Min Act: -0.1700
Data Index: 5198925 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.6129. Min Act: -0.1700
Data Index: 8269525 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.5817. Min Act: -0.1700
Data Index: 2099788 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.5817. Min Act: -0.1700
Data Index: 2600844 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.5504. Min Act: -0.1700
Data Index: 4427531 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.5504. Min Act: -0.1700
Data Index: 8328651 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.5192. Min Act: -0.1700
Data Index: 2603103 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.5192. Min Act: -0.1700
Data Index: 5772452 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.4879. Min Act: -0.1700
Data Index: 1830571 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.5192. Min Act: -0.1700
Data Index: 439232 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.4567. Min Act: -0.1700
Data Index: 8106190 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.4567. Min Act: -0.1700
Data Index: 4425893 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8942. Min Range: -6.8942
Max Act: 6.4254. Min Act: -0.1700
Data Index: 5367473 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19