Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 173 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.2608. Min Act: -0.1700
Data Index: 3459283 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.1046. Min Act: -0.1700
Data Index: 85621 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.1046. Min Act: -0.1700
Data Index: 8739254 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.1046. Min Act: -0.1700
Data Index: 8454600 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0733. Min Act: -0.1700
Data Index: 7195748 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0733. Min Act: -0.1700
Data Index: 2916970 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0733. Min Act: -0.1700
Data Index: 6731718 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0733. Min Act: -0.1700
Data Index: 285695 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0108. Min Act: -0.1700
Data Index: 8828633 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0108. Min Act: -0.1700
Data Index: 5782744 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0108. Min Act: -0.1700
Data Index: 5717674 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0108. Min Act: -0.1700
Data Index: 5405805 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0108. Min Act: -0.1700
Data Index: 8182630 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0108. Min Act: -0.1700
Data Index: 7646078 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0108. Min Act: -0.1700
Data Index: 525018 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2608. Min Range: -5.2608
Max Act: 5.0108. Min Act: -0.1700
Data Index: 6940240 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2608. Min Range: -5.2608
Max Act: 4.9796. Min Act: -0.1700
Data Index: 6057176 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2608. Min Range: -5.2608
Max Act: 4.9796. Min Act: -0.1700
Data Index: 3331584 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2608. Min Range: -5.2608
Max Act: 4.9796. Min Act: -0.1700
Data Index: 5672432 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2608. Min Range: -5.2608
Max Act: 4.9483. Min Act: -0.1700
Data Index: 2451301 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19