Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.3529. Min Act: -0.1700
Data Index: 3161758 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.3529. Min Act: -0.1700
Data Index: 6944414 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.2904. Min Act: -0.1700
Data Index: 4897487 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.2591. Min Act: -0.1700
Data Index: 4778756 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.2279. Min Act: -0.1700
Data Index: 484510 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.2279. Min Act: -0.1700
Data Index: 4180282 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1654. Min Act: -0.1700
Data Index: 8365255 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1654. Min Act: -0.1700
Data Index: 4303862 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1654. Min Act: -0.1700
Data Index: 3496296 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1654. Min Act: -0.1700
Data Index: 8654046 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1341. Min Act: -0.1700
Data Index: 3467831 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1341. Min Act: -0.1700
Data Index: 6444086 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1029. Min Act: -0.1700
Data Index: 5120047 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1341. Min Act: -0.1700
Data Index: 3567473 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1341. Min Act: -0.1700
Data Index: 4947079 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1341. Min Act: -0.1700
Data Index: 2350203 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1029. Min Act: -0.1700
Data Index: 3805720 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1029. Min Act: -0.1700
Data Index: 6473040 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1029. Min Act: -0.1700
Data Index: 8065532 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3529. Min Range: -7.3529
Max Act: 7.1029. Min Act: -0.1700
Data Index: 4670351 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19