Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.9660. Min Act: -0.1700
Data Index: 5576974 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.5597. Min Act: -0.1700
Data Index: 6341761 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.5285. Min Act: -0.1700
Data Index: 118006 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.5285. Min Act: -0.1700
Data Index: 7126988 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4972. Min Act: -0.1700
Data Index: 5890609 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4347. Min Act: -0.1700
Data Index: 8377701 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4660. Min Act: -0.1700
Data Index: 3299912 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4660. Min Act: -0.1700
Data Index: 1756273 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4347. Min Act: -0.1700
Data Index: 4087247 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1148176 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4034. Min Act: -0.1700
Data Index: 918267 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4034. Min Act: -0.1700
Data Index: 6501142 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.4034. Min Act: -0.1700
Data Index: 4199056 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.3722. Min Act: -0.1700
Data Index: 4596152 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.3722. Min Act: -0.1700
Data Index: 6153579 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.3722. Min Act: -0.1700
Data Index: 7079256 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.3409. Min Act: -0.1700
Data Index: 6030553 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.3409. Min Act: -0.1700
Data Index: 6756176 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.3409. Min Act: -0.1700
Data Index: 5657800 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9660. Min Range: -4.9660
Max Act: 4.3097. Min Act: -0.1700
Data Index: 4075598 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19