Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3775 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.5056. Min Act: -0.1700
Data Index: 7544257 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.4118. Min Act: -0.1700
Data Index: 6524338 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.2243. Min Act: -0.1700
Data Index: 239623 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.1306. Min Act: -0.1700
Data Index: 8021194 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.1618. Min Act: -0.1700
Data Index: 6097689 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.0681. Min Act: -0.1700
Data Index: 1148602 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.0368. Min Act: -0.1700
Data Index: 7888382 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.0368. Min Act: -0.1700
Data Index: 8140372 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.0056. Min Act: -0.1700
Data Index: 5230581 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.0368. Min Act: -0.1700
Data Index: 8156911 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5056. Min Range: -6.5056
Max Act: 6.0056. Min Act: -0.1700
Data Index: 7817428 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9743. Min Act: -0.1700
Data Index: 7321755 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9743. Min Act: -0.1700
Data Index: 4515361 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9743. Min Act: -0.1700
Data Index: 6051167 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9743. Min Act: -0.1700
Data Index: 6967422 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9743. Min Act: -0.1700
Data Index: 2181965 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9431. Min Act: -0.1700
Data Index: 8816325 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9431. Min Act: -0.1700
Data Index: 7245293 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9118. Min Act: -0.1700
Data Index: 607 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5056. Min Range: -6.5056
Max Act: 5.9118. Min Act: -0.1700
Data Index: 2676552 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19