Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2426. Min Range: -6.2426
Max Act: 6.2426. Min Act: -0.1700
Data Index: 8824648 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.5551. Min Act: -0.1700
Data Index: 5657056 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.5238. Min Act: -0.1700
Data Index: 6339486 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.4613. Min Act: -0.1700
Data Index: 4338697 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.4613. Min Act: -0.1700
Data Index: 14966 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.4613. Min Act: -0.1700
Data Index: 6191844 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.4301. Min Act: -0.1700
Data Index: 8474824 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.4301. Min Act: -0.1700
Data Index: 5546665 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3988. Min Act: -0.1700
Data Index: 457326 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3988. Min Act: -0.1700
Data Index: 666600 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3676. Min Act: -0.1700
Data Index: 5149966 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3363. Min Act: -0.1700
Data Index: 832821 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3676. Min Act: -0.1700
Data Index: 2276100 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3051. Min Act: -0.1700
Data Index: 4613148 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3363. Min Act: -0.1700
Data Index: 4416938 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3363. Min Act: -0.1700
Data Index: 4904676 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3363. Min Act: -0.1700
Data Index: 2591938 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3051. Min Act: -0.1700
Data Index: 4069967 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3051. Min Act: -0.1700
Data Index: 7841066 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2426. Min Range: -6.2426
Max Act: 5.3051. Min Act: -0.1700
Data Index: 5119027 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19