Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1380 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.4721. Min Act: -0.1700
Data Index: 1724509 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.4408. Min Act: -0.1700
Data Index: 1724507 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.4096. Min Act: -0.1700
Data Index: 2752118 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.3471. Min Act: -0.1700
Data Index: 1146236 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.2533. Min Act: -0.1700
Data Index: 992359 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.2221. Min Act: -0.1700
Data Index: 8240889 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.1908. Min Act: -0.1700
Data Index: 3761661 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.1596. Min Act: -0.1700
Data Index: 1417009 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.1283. Min Act: -0.1700
Data Index: 438498 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.1596. Min Act: -0.1700
Data Index: 8566452 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.1283. Min Act: -0.1700
Data Index: 614819 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.1283. Min Act: -0.1700
Data Index: 6164372 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.1283. Min Act: -0.1700
Data Index: 8563612 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.0971. Min Act: -0.1700
Data Index: 4085102 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.0971. Min Act: -0.1700
Data Index: 1893939 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.0971. Min Act: -0.1700
Data Index: 3187293 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.0971. Min Act: -0.1700
Data Index: 4520258 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.0658. Min Act: -0.1700
Data Index: 505641 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.0658. Min Act: -0.1700
Data Index: 3394252 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4721. Min Range: -4.4721
Max Act: 4.0345. Min Act: -0.1700
Data Index: 7259946 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19