Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.8633. Min Act: -0.1700
Data Index: 6503507 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.7695. Min Act: -0.1700
Data Index: 592191 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.5820. Min Act: -0.1700
Data Index: 3393417 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.5820. Min Act: -0.1700
Data Index: 2173580 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.5508. Min Act: -0.1700
Data Index: 376680 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.5508. Min Act: -0.1700
Data Index: 3281311 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.5195. Min Act: -0.1700
Data Index: 8029656 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.5195. Min Act: -0.1700
Data Index: 7440718 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.5195. Min Act: -0.1700
Data Index: 6949867 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.5195. Min Act: -0.1700
Data Index: 5761338 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4570. Min Act: -0.1700
Data Index: 5178632 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4883. Min Act: -0.1700
Data Index: 4681902 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4883. Min Act: -0.1700
Data Index: 6763669 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4258. Min Act: -0.1700
Data Index: 5724028 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4570. Min Act: -0.1700
Data Index: 7749827 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4570. Min Act: -0.1700
Data Index: 6258861 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4258. Min Act: -0.1700
Data Index: 2505204 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4570. Min Act: -0.1700
Data Index: 1086070 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4570. Min Act: -0.1700
Data Index: 6002423 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8633. Min Range: -5.8633
Max Act: 5.4883. Min Act: -0.1700
Data Index: 6138771 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19