Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.2995. Min Act: -0.1700
Data Index: 5220170 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.2370. Min Act: -0.1700
Data Index: 967028 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.1432. Min Act: -0.1700
Data Index: 4795729 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.1432. Min Act: -0.1700
Data Index: 6012723 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.0807. Min Act: -0.1700
Data Index: 5206637 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.0807. Min Act: -0.1700
Data Index: 4725527 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.0807. Min Act: -0.1700
Data Index: 597539 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.0182. Min Act: -0.1700
Data Index: 3332109 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.0182. Min Act: -0.1700
Data Index: 5549213 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2995. Min Range: -5.2995
Max Act: 5.0495. Min Act: -0.1700
Data Index: 7972596 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.9557. Min Act: -0.1700
Data Index: 4552938 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.9557. Min Act: -0.1700
Data Index: 6648644 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.9870. Min Act: -0.1700
Data Index: 2476416 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.8932. Min Act: -0.1700
Data Index: 8661578 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.8932. Min Act: -0.1700
Data Index: 3353399 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.8932. Min Act: -0.1700
Data Index: 6981945 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.8932. Min Act: -0.1700
Data Index: 6830157 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.8307. Min Act: -0.1700
Data Index: 5082920 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.8307. Min Act: -0.1700
Data Index: 3125569 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2995. Min Range: -5.2995
Max Act: 4.8620. Min Act: -0.1700
Data Index: 1141220 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19