Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.7567. Min Act: -0.1700
Data Index: 8029583 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.2567. Min Act: -0.1700
Data Index: 2098609 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.2254. Min Act: -0.1700
Data Index: 8047302 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.1629. Min Act: -0.1700
Data Index: 2776997 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.1629. Min Act: -0.1700
Data Index: 1987091 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.1317. Min Act: -0.1700
Data Index: 6521330 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.1317. Min Act: -0.1700
Data Index: 817831 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.1317. Min Act: -0.1700
Data Index: 7398474 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.1004. Min Act: -0.1700
Data Index: 6527050 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.1004. Min Act: -0.1700
Data Index: 4715658 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0692. Min Act: -0.1700
Data Index: 1028805 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0692. Min Act: -0.1700
Data Index: 6302531 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0692. Min Act: -0.1700
Data Index: 3931687 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0379. Min Act: -0.1700
Data Index: 1468080 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0379. Min Act: -0.1700
Data Index: 4737320 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0379. Min Act: -0.1700
Data Index: 5864741 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0379. Min Act: -0.1700
Data Index: 5682950 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0067. Min Act: -0.1700
Data Index: 3418556 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0067. Min Act: -0.1700
Data Index: 6719438 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7567. Min Range: -6.7567
Max Act: 6.0067. Min Act: -0.1700
Data Index: 5097494 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19