Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2446 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.2018. Min Act: -0.1700
Data Index: 5558424 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2018. Min Range: -6.2018
Max Act: 6.0456. Min Act: -0.1700
Data Index: 4488300 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.7331. Min Act: -0.1700
Data Index: 2915745 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.7331. Min Act: -0.1700
Data Index: 7103322 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.7331. Min Act: -0.1700
Data Index: 5131086 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.7018. Min Act: -0.1700
Data Index: 1522776 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.7018. Min Act: -0.1700
Data Index: 1116471 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.6706. Min Act: -0.1700
Data Index: 4392941 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.6706. Min Act: -0.1700
Data Index: 3615693 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.5143. Min Act: -0.1700
Data Index: 7064362 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.5143. Min Act: -0.1700
Data Index: 640731 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.5456. Min Act: -0.1700
Data Index: 3172654 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.5143. Min Act: -0.1700
Data Index: 1603634 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.4831. Min Act: -0.1700
Data Index: 834643 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.4831. Min Act: -0.1700
Data Index: 5906374 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.4831. Min Act: -0.1700
Data Index: 1394723 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.4518. Min Act: -0.1700
Data Index: 6576381 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.4206. Min Act: -0.1700
Data Index: 2860214 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.4518. Min Act: -0.1700
Data Index: 6468136 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2018. Min Range: -6.2018
Max Act: 5.4206. Min Act: -0.1700
Data Index: 1481243 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19