Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.8780. Min Act: -0.1700
Data Index: 3657017 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.6280. Min Act: -0.1700
Data Index: 4137641 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.4717. Min Act: -0.1700
Data Index: 4995082 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.4092. Min Act: -0.1700
Data Index: 1384452 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.2842. Min Act: -0.1700
Data Index: 1582075 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.2530. Min Act: -0.1700
Data Index: 2315420 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.2217. Min Act: -0.1700
Data Index: 4995079 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.1905. Min Act: -0.1700
Data Index: 8687164 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.1592. Min Act: -0.1700
Data Index: 3427291 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.1280. Min Act: -0.1700
Data Index: 7178125 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.0967. Min Act: -0.1700
Data Index: 8764010 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.0967. Min Act: -0.1700
Data Index: 3468553 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.0967. Min Act: -0.1700
Data Index: 3195105 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.0967. Min Act: -0.1700
Data Index: 4995088 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.0967. Min Act: -0.1700
Data Index: 7998175 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.0967. Min Act: -0.1700
Data Index: 552742 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.0655. Min Act: -0.1700
Data Index: 5469614 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8780. Min Range: -6.8780
Max Act: 6.0342. Min Act: -0.1700
Data Index: 255832 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8780. Min Range: -6.8780
Max Act: 5.9717. Min Act: -0.1700
Data Index: 3197350 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8780. Min Range: -6.8780
Max Act: 5.9405. Min Act: -0.1700
Data Index: 7391339 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19