Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.4995. Min Act: -0.1700
Data Index: 1935672 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.4057. Min Act: -0.1700
Data Index: 6516723 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.4370. Min Act: -0.1700
Data Index: 109956 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.3745. Min Act: -0.1700
Data Index: 5873815 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.3120. Min Act: -0.1700
Data Index: 2634188 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.2807. Min Act: -0.1700
Data Index: 5786752 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.2807. Min Act: -0.1700
Data Index: 6747265 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.2495. Min Act: -0.1700
Data Index: 3829390 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.2182. Min Act: -0.1700
Data Index: 1970327 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.2182. Min Act: -0.1700
Data Index: 5420268 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.1245. Min Act: -0.1700
Data Index: 2567971 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.1245. Min Act: -0.1700
Data Index: 7323805 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.1245. Min Act: -0.1700
Data Index: 5858789 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0932. Min Act: -0.1700
Data Index: 4710276 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0932. Min Act: -0.1700
Data Index: 5379347 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.1245. Min Act: -0.1700
Data Index: 2438295 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0620. Min Act: -0.1700
Data Index: 1573359 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0620. Min Act: -0.1700
Data Index: 3958863 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4995. Min Range: -6.4995
Max Act: 6.0307. Min Act: -0.1700
Data Index: 2464136 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4995. Min Range: -6.4995
Max Act: 5.9995. Min Act: -0.1700
Data Index: 2994290 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19