Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.2108. Min Act: -0.1700
Data Index: 6847122 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1795. Min Act: -0.1700
Data Index: 2341147 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1482. Min Act: -0.1700
Data Index: 6978658 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.1170. Min Act: -0.1700
Data Index: 6421043 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0545. Min Act: -0.1700
Data Index: 8159173 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0232. Min Act: -0.1700
Data Index: 575634 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0232. Min Act: -0.1700
Data Index: 4517587 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2108. Min Range: -4.2108
Max Act: 4.0232. Min Act: -0.1700
Data Index: 8515919 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9920. Min Act: -0.1700
Data Index: 1980734 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9607. Min Act: -0.1700
Data Index: 7597504 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9607. Min Act: -0.1700
Data Index: 4736563 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9607. Min Act: -0.1700
Data Index: 3072324 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9607. Min Act: -0.1700
Data Index: 3858846 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9294. Min Act: -0.1700
Data Index: 6444300 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9294. Min Act: -0.1700
Data Index: 3964382 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9294. Min Act: -0.1700
Data Index: 1900340 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9294. Min Act: -0.1700
Data Index: 7420570 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.9607. Min Act: -0.1700
Data Index: 2030825 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.8669. Min Act: -0.1700
Data Index: 2271186 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2108. Min Range: -4.2108
Max Act: 3.8982. Min Act: -0.1700
Data Index: 1072209 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19