Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5058 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0833. Min Range: -8.0833
Max Act: 8.0833. Min Act: -0.1700
Data Index: 6923367 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.9583. Min Act: -0.1700
Data Index: 7580022 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.8958. Min Act: -0.1700
Data Index: 371208 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.8958. Min Act: -0.1700
Data Index: 801032 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.8333. Min Act: -0.1700
Data Index: 5068492 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.8333. Min Act: -0.1700
Data Index: 6952814 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.8333. Min Act: -0.1700
Data Index: 5616937 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.7708. Min Act: -0.1700
Data Index: 1029282 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.7708. Min Act: -0.1700
Data Index: 4350484 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.7083. Min Act: -0.1700
Data Index: 7398885 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.7083. Min Act: -0.1700
Data Index: 3006225 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.7083. Min Act: -0.1700
Data Index: 6231826 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.7083. Min Act: -0.1700
Data Index: 4148349 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.6458. Min Act: -0.1700
Data Index: 6335649 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.6458. Min Act: -0.1700
Data Index: 629895 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.6458. Min Act: -0.1700
Data Index: 4707470 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.6458. Min Act: -0.1700
Data Index: 5277646 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.6458. Min Act: -0.1700
Data Index: 8676503 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.5833. Min Act: -0.1700
Data Index: 5250630 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0833. Min Range: -8.0833
Max Act: 7.5833. Min Act: -0.1700
Data Index: 4195475 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19