Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 933 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7621. Min Act: -0.1700
Data Index: 2351490 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7621. Min Act: -0.1700
Data Index: 369356 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7621. Min Act: -0.1700
Data Index: 1726063 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7308. Min Act: -0.1700
Data Index: 1585290 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7308. Min Act: -0.1700
Data Index: 2857708 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7621. Min Act: -0.1700
Data Index: 6511761 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7308. Min Act: -0.1700
Data Index: 7751624 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6995. Min Act: -0.1700
Data Index: 4559569 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6682. Min Act: -0.1700
Data Index: 6155753 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6369. Min Act: -0.1700
Data Index: 3015118 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6369. Min Act: -0.1700
Data Index: 4860192 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6369. Min Act: -0.1700
Data Index: 302351 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6369. Min Act: -0.1700
Data Index: 3317600 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6056. Min Act: -0.1700
Data Index: 996608 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6369. Min Act: -0.1700
Data Index: 7258310 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6369. Min Act: -0.1700
Data Index: 7245894 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5743. Min Act: -0.1700
Data Index: 6484792 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6056. Min Act: -0.1700
Data Index: 5214552 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5743. Min Act: -0.1700
Data Index: 996619 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5743. Min Act: -0.1700
Data Index: 4372092 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19