Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1550. Min Range: -4.1550
Max Act: 4.1238. Min Act: -0.1700
Data Index: 6294890 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1550. Min Range: -4.1550
Max Act: 4.1550. Min Act: -0.1700
Data Index: 6441493 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1550. Min Range: -4.1550
Max Act: 4.1238. Min Act: -0.1700
Data Index: 8505064 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1550. Min Range: -4.1550
Max Act: 4.0613. Min Act: -0.1700
Data Index: 8691412 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9675. Min Act: -0.1700
Data Index: 3785710 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9675. Min Act: -0.1700
Data Index: 538661 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9675. Min Act: -0.1700
Data Index: 3404676 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9675. Min Act: -0.1700
Data Index: 6260267 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9675. Min Act: -0.1700
Data Index: 433871 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9675. Min Act: -0.1700
Data Index: 2349375 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9987. Min Act: -0.1700
Data Index: 7222091 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9362. Min Act: -0.1700
Data Index: 3010697 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9675. Min Act: -0.1700
Data Index: 7071843 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9362. Min Act: -0.1700
Data Index: 7219707 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9675. Min Act: -0.1700
Data Index: 6195238 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9050. Min Act: -0.1700
Data Index: 3010679 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9050. Min Act: -0.1700
Data Index: 8087318 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.9050. Min Act: -0.1700
Data Index: 4693984 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.8737. Min Act: -0.1700
Data Index: 4681004 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1550. Min Range: -4.1550
Max Act: 3.8737. Min Act: -0.1700
Data Index: 431552 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19