Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.6102. Min Act: -0.1700
Data Index: 3949593 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.5790. Min Act: -0.1700
Data Index: 3477289 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.5165. Min Act: -0.1700
Data Index: 3600503 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.5165. Min Act: -0.1700
Data Index: 7610667 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4852. Min Act: -0.1700
Data Index: 1783460 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4540. Min Act: -0.1700
Data Index: 5000872 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4540. Min Act: -0.1700
Data Index: 2584938 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4227. Min Act: -0.1700
Data Index: 4492823 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4540. Min Act: -0.1700
Data Index: 7803272 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.4852. Min Act: -0.1700
Data Index: 7671613 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3915. Min Act: -0.1700
Data Index: 6364311 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3602. Min Act: -0.1700
Data Index: 3667757 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3602. Min Act: -0.1700
Data Index: 1055572 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3915. Min Act: -0.1700
Data Index: 6743781 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3602. Min Act: -0.1700
Data Index: 492455 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3290. Min Act: -0.1700
Data Index: 6213354 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3915. Min Act: -0.1700
Data Index: 196855 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3602. Min Act: -0.1700
Data Index: 1281523 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3290. Min Act: -0.1700
Data Index: 2089367 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6102. Min Range: -4.6102
Max Act: 4.3602. Min Act: -0.1700
Data Index: 5426031 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19