Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1107 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.6920. Min Act: -0.1700
Data Index: 1153345 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.6608. Min Act: -0.1700
Data Index: 6092170 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.2233. Min Act: -0.1700
Data Index: 6737281 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.1920. Min Act: -0.1700
Data Index: 3291808 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.1920. Min Act: -0.1700
Data Index: 4780767 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.1295. Min Act: -0.1700
Data Index: 599138 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.1295. Min Act: -0.1700
Data Index: 2117343 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0983. Min Act: -0.1700
Data Index: 948944 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0358. Min Act: -0.1700
Data Index: 4960891 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0670. Min Act: -0.1700
Data Index: 4410276 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0670. Min Act: -0.1700
Data Index: 2660300 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0670. Min Act: -0.1700
Data Index: 1460205 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0670. Min Act: -0.1700
Data Index: 3157704 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0358. Min Act: -0.1700
Data Index: 6911315 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0358. Min Act: -0.1700
Data Index: 1454196 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0358. Min Act: -0.1700
Data Index: 1105231 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0045. Min Act: -0.1700
Data Index: 78352 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0045. Min Act: -0.1700
Data Index: 4970194 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6920. Min Range: -6.6920
Max Act: 6.0045. Min Act: -0.1700
Data Index: 3825335 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6920. Min Range: -6.6920
Max Act: 5.9733. Min Act: -0.1700
Data Index: 6122155 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19