Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.7457. Min Act: -0.1700
Data Index: 209595 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.4020. Min Act: -0.1700
Data Index: 6408949 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.4020. Min Act: -0.1700
Data Index: 664009 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.4020. Min Act: -0.1700
Data Index: 8616331 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.3707. Min Act: -0.1700
Data Index: 3315152 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.3082. Min Act: -0.1700
Data Index: 7325399 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.2145. Min Act: -0.1700
Data Index: 1324677 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.2145. Min Act: -0.1700
Data Index: 2127374 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.1832. Min Act: -0.1700
Data Index: 269584 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.1520. Min Act: -0.1700
Data Index: 5342754 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.1207. Min Act: -0.1700
Data Index: 6219279 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.1207. Min Act: -0.1700
Data Index: 4173253 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.1207. Min Act: -0.1700
Data Index: 8775136 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.1207. Min Act: -0.1700
Data Index: 1885999 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.0895. Min Act: -0.1700
Data Index: 726606 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.0895. Min Act: -0.1700
Data Index: 8060906 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.0895. Min Act: -0.1700
Data Index: 7582074 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.0582. Min Act: -0.1700
Data Index: 2609976 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.0582. Min Act: -0.1700
Data Index: 7711378 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7457. Min Range: -7.7457
Max Act: 7.0270. Min Act: -0.1700
Data Index: 4079962 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19