Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1564 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.5621. Min Act: -0.1700
Data Index: 274484 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.5309. Min Act: -0.1700
Data Index: 8331018 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.4371. Min Act: -0.1700
Data Index: 5271348 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.4059. Min Act: -0.1700
Data Index: 4769324 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.3746. Min Act: -0.1700
Data Index: 5147419 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.3434. Min Act: -0.1700
Data Index: 3479836 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.3121. Min Act: -0.1700
Data Index: 5290588 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.2809. Min Act: -0.1700
Data Index: 3852958 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.2809. Min Act: -0.1700
Data Index: 5750759 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.2496. Min Act: -0.1700
Data Index: 5132774 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.2184. Min Act: -0.1700
Data Index: 707414 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1871. Min Act: -0.1700
Data Index: 5313969 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 3131052 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 7803544 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 5698021 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 4275208 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 581137 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0934. Min Act: -0.1700
Data Index: 7072953 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.1246. Min Act: -0.1700
Data Index: 174280 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5621. Min Range: -5.5621
Max Act: 5.0621. Min Act: -0.1700
Data Index: 4109009 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19