Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2489 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.4649. Min Act: -0.1700
Data Index: 1995556 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.2774. Min Act: -0.1700
Data Index: 1722624 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.2462. Min Act: -0.1700
Data Index: 2206219 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.2462. Min Act: -0.1700
Data Index: 4838190 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.2149. Min Act: -0.1700
Data Index: 5733617 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.1524. Min Act: -0.1700
Data Index: 8778563 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.1524. Min Act: -0.1700
Data Index: 7776541 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.0899. Min Act: -0.1700
Data Index: 6641305 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.0587. Min Act: -0.1700
Data Index: 4114386 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.0587. Min Act: -0.1700
Data Index: 7965970 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.0274. Min Act: -0.1700
Data Index: 5286672 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4649. Min Range: -6.4649
Max Act: 6.0274. Min Act: -0.1700
Data Index: 7079647 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4649. Min Range: -6.4649
Max Act: 5.9962. Min Act: -0.1700
Data Index: 4179070 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4649. Min Range: -6.4649
Max Act: 5.9649. Min Act: -0.1700
Data Index: 5990592 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4649. Min Range: -6.4649
Max Act: 5.9649. Min Act: -0.1700
Data Index: 5746916 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4649. Min Range: -6.4649
Max Act: 5.9649. Min Act: -0.1700
Data Index: 6852957 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4649. Min Range: -6.4649
Max Act: 5.9337. Min Act: -0.1700
Data Index: 7114545 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4649. Min Range: -6.4649
Max Act: 5.9024. Min Act: -0.1700
Data Index: 1025958 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4649. Min Range: -6.4649
Max Act: 5.9337. Min Act: -0.1700
Data Index: 4979609 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4649. Min Range: -6.4649
Max Act: 5.9024. Min Act: -0.1700
Data Index: 4980476 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19