Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 903 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.8652. Min Act: -0.1700
Data Index: 8273285 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.6464. Min Act: -0.1700
Data Index: 134480 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.5839. Min Act: -0.1700
Data Index: 2172538 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.5839. Min Act: -0.1700
Data Index: 4593 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.4902. Min Act: -0.1700
Data Index: 5739130 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.5214. Min Act: -0.1700
Data Index: 4594916 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.4589. Min Act: -0.1700
Data Index: 8231035 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3964. Min Act: -0.1700
Data Index: 6291838 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3964. Min Act: -0.1700
Data Index: 7942342 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3964. Min Act: -0.1700
Data Index: 4441227 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3964. Min Act: -0.1700
Data Index: 3949879 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3652. Min Act: -0.1700
Data Index: 1638600 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3652. Min Act: -0.1700
Data Index: 3211198 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3339. Min Act: -0.1700
Data Index: 2322908 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3339. Min Act: -0.1700
Data Index: 7044586 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3339. Min Act: -0.1700
Data Index: 2162459 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3339. Min Act: -0.1700
Data Index: 1103336 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3652. Min Act: -0.1700
Data Index: 8287003 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3339. Min Act: -0.1700
Data Index: 8318046 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8652. Min Range: -5.8652
Max Act: 5.3027. Min Act: -0.1700
Data Index: 3561547 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19