Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4616920 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.4354. Min Act: -0.1700
Data Index: 5549820 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.4354. Min Act: -0.1700
Data Index: 4314860 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.4041. Min Act: -0.1700
Data Index: 5440842 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.3104. Min Act: -0.1700
Data Index: 1395278 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.2791. Min Act: -0.1700
Data Index: 815139 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.2166. Min Act: -0.1700
Data Index: 5567273 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.2166. Min Act: -0.1700
Data Index: 3090097 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.1854. Min Act: -0.1700
Data Index: 97105 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.1854. Min Act: -0.1700
Data Index: 735320 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.1854. Min Act: -0.1700
Data Index: 6647150 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.1229. Min Act: -0.1700
Data Index: 7332165 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.0604. Min Act: -0.1700
Data Index: 5407166 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.0916. Min Act: -0.1700
Data Index: 4720988 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7791. Min Range: -5.7791
Max Act: 5.0291. Min Act: -0.1700
Data Index: 1232132 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7791. Min Range: -5.7791
Max Act: 4.9979. Min Act: -0.1700
Data Index: 279185 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7791. Min Range: -5.7791
Max Act: 4.9979. Min Act: -0.1700
Data Index: 6745037 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7791. Min Range: -5.7791
Max Act: 4.9979. Min Act: -0.1700
Data Index: 3289017 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7791. Min Range: -5.7791
Max Act: 4.9666. Min Act: -0.1700
Data Index: 5190054 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7791. Min Range: -5.7791
Max Act: 4.9979. Min Act: -0.1700
Data Index: 1902422 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19