Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5900 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0920. Min Range: -5.0920
Max Act: 5.0920. Min Act: -0.1700
Data Index: 7246002 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.9670. Min Act: -0.1700
Data Index: 666596 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.9670. Min Act: -0.1700
Data Index: 3343800 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.9358. Min Act: -0.1700
Data Index: 8044827 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.9045. Min Act: -0.1700
Data Index: 410258 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.8733. Min Act: -0.1700
Data Index: 8824406 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.8420. Min Act: -0.1700
Data Index: 3298286 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.8420. Min Act: -0.1700
Data Index: 7627757 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.8108. Min Act: -0.1700
Data Index: 1774870 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7483. Min Act: -0.1700
Data Index: 8423402 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7795. Min Act: -0.1700
Data Index: 4351230 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7170. Min Act: -0.1700
Data Index: 7212469 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7483. Min Act: -0.1700
Data Index: 6455234 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7170. Min Act: -0.1700
Data Index: 8556636 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7170. Min Act: -0.1700
Data Index: 3033984 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7170. Min Act: -0.1700
Data Index: 6983019 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7170. Min Act: -0.1700
Data Index: 6379591 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7170. Min Act: -0.1700
Data Index: 6455246 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7170. Min Act: -0.1700
Data Index: 2783647 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0920. Min Range: -5.0920
Max Act: 4.7483. Min Act: -0.1700
Data Index: 1774446 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19