Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3321 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2035. Min Range: -6.2035
Max Act: 6.2035. Min Act: -0.1700
Data Index: 1215396 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2035. Min Range: -6.2035
Max Act: 6.1410. Min Act: -0.1700
Data Index: 8506354 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2035. Min Range: -6.2035
Max Act: 6.0473. Min Act: -0.1700
Data Index: 1255333 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2035. Min Range: -6.2035
Max Act: 6.0473. Min Act: -0.1700
Data Index: 4854180 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2035. Min Range: -6.2035
Max Act: 6.0473. Min Act: -0.1700
Data Index: 4962318 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2035. Min Range: -6.2035
Max Act: 6.0473. Min Act: -0.1700
Data Index: 7574437 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.9848. Min Act: -0.1700
Data Index: 7574439 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.9848. Min Act: -0.1700
Data Index: 5767151 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.9535. Min Act: -0.1700
Data Index: 4962321 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.9535. Min Act: -0.1700
Data Index: 3375995 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.9223. Min Act: -0.1700
Data Index: 1255336 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.8910. Min Act: -0.1700
Data Index: 4828507 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.8598. Min Act: -0.1700
Data Index: 2409250 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.7973. Min Act: -0.1700
Data Index: 8286509 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.7973. Min Act: -0.1700
Data Index: 3655903 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.7660. Min Act: -0.1700
Data Index: 4828500 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.7660. Min Act: -0.1700
Data Index: 732077 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.7660. Min Act: -0.1700
Data Index: 1797742 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.7348. Min Act: -0.1700
Data Index: 4832873 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2035. Min Range: -6.2035
Max Act: 5.7348. Min Act: -0.1700
Data Index: 1230059 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19