Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 697 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.3870. Min Act: -0.1700
Data Index: 646876 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.3558. Min Act: -0.1700
Data Index: 4738052 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.2308. Min Act: -0.1700
Data Index: 4484563 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.2308. Min Act: -0.1700
Data Index: 2846341 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.2308. Min Act: -0.1700
Data Index: 4130145 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.1683. Min Act: -0.1700
Data Index: 59671 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.1058. Min Act: -0.1700
Data Index: 3243339 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.1370. Min Act: -0.1700
Data Index: 3347976 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.0433. Min Act: -0.1700
Data Index: 3422618 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3870. Min Range: -7.3870
Max Act: 7.0120. Min Act: -0.1700
Data Index: 6974229 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.9808. Min Act: -0.1700
Data Index: 3359791 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.9808. Min Act: -0.1700
Data Index: 539239 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.9495. Min Act: -0.1700
Data Index: 6958607 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.9183. Min Act: -0.1700
Data Index: 5546141 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.8870. Min Act: -0.1700
Data Index: 6720386 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.8245. Min Act: -0.1700
Data Index: 3058846 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.7933. Min Act: -0.1700
Data Index: 1219200 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.7933. Min Act: -0.1700
Data Index: 7658055 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.6995. Min Act: -0.1700
Data Index: 8570391 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3870. Min Range: -7.3870
Max Act: 6.6995. Min Act: -0.1700
Data Index: 7942850 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19