Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.3776. Min Act: -0.1700
Data Index: 1118645 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.3776. Min Act: -0.1700
Data Index: 5555484 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.3464. Min Act: -0.1700
Data Index: 969369 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.3151. Min Act: -0.1700
Data Index: 1940529 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.3464. Min Act: -0.1700
Data Index: 6095348 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.3151. Min Act: -0.1700
Data Index: 3364781 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2839. Min Act: -0.1700
Data Index: 465803 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2839. Min Act: -0.1700
Data Index: 5728814 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2839. Min Act: -0.1700
Data Index: 4178118 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2839. Min Act: -0.1700
Data Index: 275891 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2839. Min Act: -0.1700
Data Index: 8178542 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2526. Min Act: -0.1700
Data Index: 5736137 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2526. Min Act: -0.1700
Data Index: 5682100 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2526. Min Act: -0.1700
Data Index: 8245712 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2526. Min Act: -0.1700
Data Index: 8069392 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2839. Min Act: -0.1700
Data Index: 7532490 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2526. Min Act: -0.1700
Data Index: 7425098 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2526. Min Act: -0.1700
Data Index: 3946727 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2526. Min Act: -0.1700
Data Index: 5760126 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3776. Min Range: -4.3776
Max Act: 4.2526. Min Act: -0.1700
Data Index: 3539690 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19