Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4427 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.6480. Min Act: -0.1700
Data Index: 4532387 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.4293. Min Act: -0.1700
Data Index: 1994892 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.3980. Min Act: -0.1700
Data Index: 2064306 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.3980. Min Act: -0.1700
Data Index: 3708162 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.3043. Min Act: -0.1700
Data Index: 5733608 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.2418. Min Act: -0.1700
Data Index: 1823516 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.0543. Min Act: -0.1700
Data Index: 8584567 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.0543. Min Act: -0.1700
Data Index: 7745165 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.0543. Min Act: -0.1700
Data Index: 4544407 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.0230. Min Act: -0.1700
Data Index: 8447322 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.0230. Min Act: -0.1700
Data Index: 718531 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6480. Min Range: -6.6480
Max Act: 6.0230. Min Act: -0.1700
Data Index: 6273462 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6480. Min Range: -6.6480
Max Act: 5.9605. Min Act: -0.1700
Data Index: 7076768 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6480. Min Range: -6.6480
Max Act: 5.8668. Min Act: -0.1700
Data Index: 2134985 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6480. Min Range: -6.6480
Max Act: 5.8668. Min Act: -0.1700
Data Index: 5589156 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6480. Min Range: -6.6480
Max Act: 5.8668. Min Act: -0.1700
Data Index: 6973751 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6480. Min Range: -6.6480
Max Act: 5.8355. Min Act: -0.1700
Data Index: 3910950 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6480. Min Range: -6.6480
Max Act: 5.8355. Min Act: -0.1700
Data Index: 8529551 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6480. Min Range: -6.6480
Max Act: 5.8668. Min Act: -0.1700
Data Index: 8029887 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6480. Min Range: -6.6480
Max Act: 5.8355. Min Act: -0.1700
Data Index: 3370192 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19