Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4414 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.9803. Min Act: -0.1700
Data Index: 8115700 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.8553. Min Act: -0.1700
Data Index: 342921 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.7928. Min Act: -0.1700
Data Index: 6905519 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.6678. Min Act: -0.1700
Data Index: 4849849 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.6053. Min Act: -0.1700
Data Index: 7129081 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.6053. Min Act: -0.1700
Data Index: 6888570 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.6053. Min Act: -0.1700
Data Index: 5759389 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.6053. Min Act: -0.1700
Data Index: 2346296 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.6053. Min Act: -0.1700
Data Index: 1406040 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.6678. Min Act: -0.1700
Data Index: 2626311 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.5428. Min Act: -0.1700
Data Index: 6826799 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.4803. Min Act: -0.1700
Data Index: 3709304 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.4178. Min Act: -0.1700
Data Index: 4172065 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.5428. Min Act: -0.1700
Data Index: 1396976 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.4803. Min Act: -0.1700
Data Index: 8125675 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.4803. Min Act: -0.1700
Data Index: 4036585 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.4803. Min Act: -0.1700
Data Index: 3995051 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.4803. Min Act: -0.1700
Data Index: 2269194 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.4803. Min Act: -0.1700
Data Index: 6878125 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9803. Min Range: -8.9803
Max Act: 8.4178. Min Act: -0.1700
Data Index: 4414299 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19