Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4252 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.2853. Min Act: -0.1700
Data Index: 7317234 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.2228. Min Act: -0.1700
Data Index: 1413384 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.1916. Min Act: -0.1700
Data Index: 8283100 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.1291. Min Act: -0.1700
Data Index: 2879687 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.1291. Min Act: -0.1700
Data Index: 1855424 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.0978. Min Act: -0.1700
Data Index: 7977957 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.0666. Min Act: -0.1700
Data Index: 3318834 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.0353. Min Act: -0.1700
Data Index: 456577 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2853. Min Range: -7.2853
Max Act: 7.0041. Min Act: -0.1700
Data Index: 7413611 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.9416. Min Act: -0.1700
Data Index: 1891789 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.9728. Min Act: -0.1700
Data Index: 7472073 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.9416. Min Act: -0.1700
Data Index: 3494487 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.9103. Min Act: -0.1700
Data Index: 913501 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.9103. Min Act: -0.1700
Data Index: 6075194 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.8791. Min Act: -0.1700
Data Index: 6309187 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.9103. Min Act: -0.1700
Data Index: 3257700 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.8478. Min Act: -0.1700
Data Index: 8172665 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.8166. Min Act: -0.1700
Data Index: 4416184 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.8166. Min Act: -0.1700
Data Index: 3843604 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2853. Min Range: -7.2853
Max Act: 6.8166. Min Act: -0.1700
Data Index: 3531452 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19