Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 196 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.2291. Min Act: -0.1700
Data Index: 1757640 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.1666. Min Act: -0.1700
Data Index: 6645918 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.1353. Min Act: -0.1700
Data Index: 7016724 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.1041. Min Act: -0.1700
Data Index: 7048535 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0728. Min Act: -0.1700
Data Index: 3009071 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0728. Min Act: -0.1700
Data Index: 3261232 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0728. Min Act: -0.1700
Data Index: 7652542 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 5202930 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 4647421 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0728. Min Act: -0.1700
Data Index: 5918073 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 373614 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 304128 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0103. Min Act: -0.1700
Data Index: 7586418 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0416. Min Act: -0.1700
Data Index: 1956266 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0103. Min Act: -0.1699
Data Index: 1948472 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0103. Min Act: -0.1700
Data Index: 3910369 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.9791. Min Act: -0.1700
Data Index: 7119496 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2291. Min Range: -6.2291
Max Act: 6.0103. Min Act: -0.1700
Data Index: 5629069 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.9791. Min Act: -0.1700
Data Index: 8294444 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2291. Min Range: -6.2291
Max Act: 5.9166. Min Act: -0.1700
Data Index: 8169867 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19