Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5871 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.5023. Min Act: -0.1700
Data Index: 5174570 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.3148. Min Act: -0.1700
Data Index: 5174581 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.2835. Min Act: -0.1700
Data Index: 1978666 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.2210. Min Act: -0.1700
Data Index: 6986898 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.1273. Min Act: -0.1700
Data Index: 4610584 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.1585. Min Act: -0.1700
Data Index: 2710211 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.1273. Min Act: -0.1700
Data Index: 13371 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.1273. Min Act: -0.1700
Data Index: 5142972 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.1273. Min Act: -0.1700
Data Index: 465090 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0648. Min Act: -0.1700
Data Index: 20035 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0960. Min Act: -0.1700
Data Index: 7254352 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0960. Min Act: -0.1700
Data Index: 8060920 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0960. Min Act: -0.1700
Data Index: 6843370 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0960. Min Act: -0.1700
Data Index: 1491362 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0960. Min Act: -0.1700
Data Index: 1845595 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0648. Min Act: -0.1700
Data Index: 1989054 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0648. Min Act: -0.1700
Data Index: 7635191 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0648. Min Act: -0.1700
Data Index: 1167697 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0648. Min Act: -0.1700
Data Index: 6986883 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5023. Min Range: -5.5023
Max Act: 5.0335. Min Act: -0.1700
Data Index: 6538351 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19