Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4713 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1621. Min Range: -8.1621
Max Act: 8.1621. Min Act: -0.1700
Data Index: 3782211 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1621. Min Range: -8.1621
Max Act: 8.0996. Min Act: -0.1700
Data Index: 1725691 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1621. Min Range: -8.1621
Max Act: 8.0371. Min Act: -0.1700
Data Index: 1497095 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1621. Min Range: -8.1621
Max Act: 8.0371. Min Act: -0.1700
Data Index: 6017555 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1621. Min Range: -8.1621
Max Act: 8.0371. Min Act: -0.1700
Data Index: 7982586 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.9746. Min Act: -0.1700
Data Index: 7086720 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.9746. Min Act: -0.1700
Data Index: 1299967 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.8184. Min Act: -0.1700
Data Index: 6281533 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.8496. Min Act: -0.1700
Data Index: 7786705 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.7871. Min Act: -0.1700
Data Index: 7769564 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.7559. Min Act: -0.1700
Data Index: 6813485 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.7559. Min Act: -0.1700
Data Index: 3950566 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.7246. Min Act: -0.1700
Data Index: 4606963 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.7246. Min Act: -0.1700
Data Index: 542999 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.6934. Min Act: -0.1700
Data Index: 303022 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.7246. Min Act: -0.1700
Data Index: 5601913 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.6621. Min Act: -0.1700
Data Index: 349172 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.6621. Min Act: -0.1700
Data Index: 4573128 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.6621. Min Act: -0.1700
Data Index: 3331940 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1621. Min Range: -8.1621
Max Act: 7.6309. Min Act: -0.1700
Data Index: 7834459 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19