Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.7189. Min Act: -0.1700
Data Index: 2779925 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.6564. Min Act: -0.1700
Data Index: 2847427 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.5314. Min Act: -0.1700
Data Index: 4942626 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.5314. Min Act: -0.1700
Data Index: 427009 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.4064. Min Act: -0.1700
Data Index: 5072206 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.4376. Min Act: -0.1700
Data Index: 3141730 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.3751. Min Act: -0.1700
Data Index: 6166495 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.3751. Min Act: -0.1700
Data Index: 4833084 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.3439. Min Act: -0.1700
Data Index: 1690970 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.3439. Min Act: -0.1700
Data Index: 2326334 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.3439. Min Act: -0.1700
Data Index: 7915275 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.3439. Min Act: -0.1700
Data Index: 1733465 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.3126. Min Act: -0.1700
Data Index: 1616305 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.2814. Min Act: -0.1700
Data Index: 714731 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.2501. Min Act: -0.1700
Data Index: 762972 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.2814. Min Act: -0.1700
Data Index: 2785108 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.2814. Min Act: -0.1700
Data Index: 4413907 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.2189. Min Act: -0.1700
Data Index: 4539779 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.2189. Min Act: -0.1700
Data Index: 2641588 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7189. Min Range: -6.7189
Max Act: 6.1876. Min Act: -0.1700
Data Index: 1654197 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19