Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.7757. Min Act: -0.1700
Data Index: 3514926 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.7600. Min Act: -0.1700
Data Index: 368496 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.7600. Min Act: -0.1700
Data Index: 8460810 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.7287. Min Act: -0.1700
Data Index: 6220176 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.7287. Min Act: -0.1700
Data Index: 211350 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.6818. Min Act: -0.1700
Data Index: 4652482 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.6505. Min Act: -0.1700
Data Index: 8620069 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.6505. Min Act: -0.1700
Data Index: 7857686 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.6192. Min Act: -0.1700
Data Index: 5695117 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.6036. Min Act: -0.1700
Data Index: 3256971 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.6192. Min Act: -0.1700
Data Index: 1998302 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.5879. Min Act: -0.1700
Data Index: 4097993 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.6192. Min Act: -0.1700
Data Index: 57439 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.6036. Min Act: -0.1700
Data Index: 3470081 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.5879. Min Act: -0.1700
Data Index: 8103656 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.5723. Min Act: -0.1700
Data Index: 2953207 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.5410. Min Act: -0.1700
Data Index: 5562233 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.5410. Min Act: -0.1700
Data Index: 8241670 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.5096. Min Act: -0.1700
Data Index: 5950706 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7757. Min Range: -3.7757
Max Act: 3.5096. Min Act: -0.1700
Data Index: 7468648 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19