Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0681. Min Range: -5.0681
Max Act: 5.0681. Min Act: -0.1700
Data Index: 2139479 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0681. Min Range: -5.0681
Max Act: 5.0369. Min Act: -0.1700
Data Index: 8230599 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0681. Min Range: -5.0681
Max Act: 5.0681. Min Act: -0.1700
Data Index: 1176232 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0681. Min Range: -5.0681
Max Act: 5.0056. Min Act: -0.1700
Data Index: 8477055 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0681. Min Range: -5.0681
Max Act: 5.0681. Min Act: -0.1700
Data Index: 6023617 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.9431. Min Act: -0.1700
Data Index: 5725527 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0681. Min Range: -5.0681
Max Act: 5.0056. Min Act: -0.1700
Data Index: 2670734 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.9119. Min Act: -0.1700
Data Index: 2047137 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.9431. Min Act: -0.1700
Data Index: 4889117 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0681. Min Range: -5.0681
Max Act: 5.0369. Min Act: -0.1700
Data Index: 1125598 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.9119. Min Act: -0.1700
Data Index: 2670733 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.9119. Min Act: -0.1700
Data Index: 3726092 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.8494. Min Act: -0.1700
Data Index: 6166817 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.8806. Min Act: -0.1700
Data Index: 4007347 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.9119. Min Act: -0.1700
Data Index: 1571830 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.8494. Min Act: -0.1700
Data Index: 3114365 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.7869. Min Act: -0.1700
Data Index: 686174 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.8494. Min Act: -0.1700
Data Index: 798893 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.8181. Min Act: -0.1700
Data Index: 5898039 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0681. Min Range: -5.0681
Max Act: 4.8806. Min Act: -0.1700
Data Index: 4027198 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19