Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5882 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1627. Min Range: -7.1627
Max Act: 7.1627. Min Act: -0.1700
Data Index: 38516 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1627. Min Range: -7.1627
Max Act: 7.1627. Min Act: -0.1700
Data Index: 1011610 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1627. Min Range: -7.1627
Max Act: 7.1002. Min Act: -0.1700
Data Index: 6967865 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1627. Min Range: -7.1627
Max Act: 7.0064. Min Act: -0.1699
Data Index: 1619284 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1627. Min Range: -7.1627
Max Act: 7.0064. Min Act: -0.1700
Data Index: 7984564 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.9752. Min Act: -0.1700
Data Index: 1816409 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.9752. Min Act: -0.1700
Data Index: 2417304 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.9439. Min Act: -0.1700
Data Index: 1864029 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.9127. Min Act: -0.1700
Data Index: 241190 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.9127. Min Act: -0.1700
Data Index: 4989941 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.9127. Min Act: -0.1700
Data Index: 6742572 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 6639299 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8814. Min Act: -0.1700
Data Index: 5263267 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 4042829 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 482349 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 8134680 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8189. Min Act: -0.1700
Data Index: 6495208 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8189. Min Act: -0.1700
Data Index: 2458601 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8189. Min Act: -0.1700
Data Index: 3601093 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1627. Min Range: -7.1627
Max Act: 6.8502. Min Act: -0.1700
Data Index: 5294086 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19