Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 326 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.3432. Min Act: -0.1700
Data Index: 8698216 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.3119. Min Act: -0.1700
Data Index: 3591202 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.1244. Min Act: -0.1700
Data Index: 4444069 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.0932. Min Act: -0.1700
Data Index: 3231924 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.0932. Min Act: -0.1700
Data Index: 6160511 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.0619. Min Act: -0.1700
Data Index: 3517564 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.0619. Min Act: -0.1700
Data Index: 4032888 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.0619. Min Act: -0.1700
Data Index: 6346320 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3432. Min Range: -6.3432
Max Act: 6.0307. Min Act: -0.1700
Data Index: 1235451 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9994. Min Act: -0.1700
Data Index: 4117483 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9682. Min Act: -0.1700
Data Index: 2666046 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9682. Min Act: -0.1700
Data Index: 4590149 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9682. Min Act: -0.1700
Data Index: 500410 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9682. Min Act: -0.1700
Data Index: 8292713 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9369. Min Act: -0.1700
Data Index: 7116582 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9369. Min Act: -0.1700
Data Index: 1819159 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9369. Min Act: -0.1700
Data Index: 7201256 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9057. Min Act: -0.1700
Data Index: 1513335 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9057. Min Act: -0.1700
Data Index: 1929008 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3432. Min Range: -6.3432
Max Act: 5.9057. Min Act: -0.1700
Data Index: 4251431 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19