Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1615 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2095. Min Range: -7.2095
Max Act: 7.2095. Min Act: -0.1700
Data Index: 7446169 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2095. Min Range: -7.2095
Max Act: 7.0845. Min Act: -0.1700
Data Index: 7250832 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2095. Min Range: -7.2095
Max Act: 7.0532. Min Act: -0.1700
Data Index: 7446170 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.9282. Min Act: -0.1700
Data Index: 2224591 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.9282. Min Act: -0.1700
Data Index: 3220662 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8970. Min Act: -0.1700
Data Index: 4456164 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8970. Min Act: -0.1700
Data Index: 1489801 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8970. Min Act: -0.1700
Data Index: 2491538 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8970. Min Act: -0.1700
Data Index: 2023468 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8657. Min Act: -0.1700
Data Index: 240348 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8345. Min Act: -0.1700
Data Index: 8436141 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8345. Min Act: -0.1700
Data Index: 8068806 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8032. Min Act: -0.1700
Data Index: 6145627 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8032. Min Act: -0.1700
Data Index: 7763886 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8032. Min Act: -0.1700
Data Index: 4327974 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.7720. Min Act: -0.1700
Data Index: 2538270 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.8032. Min Act: -0.1700
Data Index: 1721228 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.7720. Min Act: -0.1700
Data Index: 8807327 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.7720. Min Act: -0.1700
Data Index: 6854553 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2095. Min Range: -7.2095
Max Act: 6.7720. Min Act: -0.1700
Data Index: 7093017 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19