Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1149 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1772. Min Act: -0.1700
Data Index: 129897 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1105. Min Act: -0.1700
Data Index: 4127159 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1606. Min Act: -0.1700
Data Index: 4757551 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1439. Min Act: -0.1700
Data Index: 6563819 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1272. Min Act: -0.1700
Data Index: 4435311 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1105. Min Act: -0.1700
Data Index: 3645567 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1606. Min Act: -0.1671
Data Index: 3387931 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1439. Min Act: -0.1700
Data Index: 3556955 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1272. Min Act: -0.1700
Data Index: 3193659 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1272. Min Act: -0.1699
Data Index: 1653916 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.0770. Min Act: -0.1699
Data Index: 4505650 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1105. Min Act: -0.1700
Data Index: 1027790 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1105. Min Act: -0.1700
Data Index: 7340589 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.0937. Min Act: -0.1700
Data Index: 3648144 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.0937. Min Act: -0.1698
Data Index: 1340998 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1105. Min Act: -0.1686
Data Index: 4424749 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.1105. Min Act: -0.1694
Data Index: 314863 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.0937. Min Act: -0.1697
Data Index: 5680493 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.0937. Min Act: -0.1700
Data Index: 6175070 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1772. Min Range: -2.1772
Max Act: 2.0937. Min Act: -0.1700
Data Index: 4336130 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19