Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4058 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1969. Min Range: -8.1969
Max Act: 8.1969. Min Act: -0.1700
Data Index: 4095272 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1969. Min Range: -8.1969
Max Act: 8.0094. Min Act: -0.1700
Data Index: 7949508 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1969. Min Range: -8.1969
Max Act: 8.0719. Min Act: -0.1700
Data Index: 4967665 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.6969. Min Act: -0.1700
Data Index: 5195726 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.6032. Min Act: -0.1700
Data Index: 4646831 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.5719. Min Act: -0.1700
Data Index: 5884717 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.5094. Min Act: -0.1700
Data Index: 7558072 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.4782. Min Act: -0.1700
Data Index: 2975908 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.4157. Min Act: -0.1700
Data Index: 6140321 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.4157. Min Act: -0.1700
Data Index: 3988172 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.3532. Min Act: -0.1700
Data Index: 1566286 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.3219. Min Act: -0.1700
Data Index: 969460 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.2907. Min Act: -0.1700
Data Index: 3729000 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.2282. Min Act: -0.1700
Data Index: 459618 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.2282. Min Act: -0.1700
Data Index: 3840265 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.1969. Min Act: -0.1700
Data Index: 380844 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.1657. Min Act: -0.1700
Data Index: 6322646 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.1344. Min Act: -0.1700
Data Index: 5422833 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.0719. Min Act: -0.1700
Data Index: 3122113 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1969. Min Range: -8.1969
Max Act: 7.0719. Min Act: -0.1700
Data Index: 1660013 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19