Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3944. Min Range: -6.3944
Max Act: 6.3944. Min Act: -0.1700
Data Index: 457414 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3944. Min Range: -6.3944
Max Act: 6.3944. Min Act: -0.1700
Data Index: 1290899 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3944. Min Range: -6.3944
Max Act: 6.1444. Min Act: -0.1700
Data Index: 184639 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3944. Min Range: -6.3944
Max Act: 6.1444. Min Act: -0.1700
Data Index: 6656549 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3944. Min Range: -6.3944
Max Act: 6.1444. Min Act: -0.1700
Data Index: 8749662 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3944. Min Range: -6.3944
Max Act: 6.0819. Min Act: -0.1700
Data Index: 2052442 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.9881. Min Act: -0.1700
Data Index: 561580 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.9256. Min Act: -0.1700
Data Index: 3378300 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.9256. Min Act: -0.1700
Data Index: 296968 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.9256. Min Act: -0.1700
Data Index: 1353021 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.9256. Min Act: -0.1700
Data Index: 3667807 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8944. Min Act: -0.1700
Data Index: 2473471 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8944. Min Act: -0.1700
Data Index: 1135953 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8944. Min Act: -0.1700
Data Index: 1427529 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8319. Min Act: -0.1700
Data Index: 2590883 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8631. Min Act: -0.1700
Data Index: 1435149 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8006. Min Act: -0.1700
Data Index: 7419446 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8319. Min Act: -0.1700
Data Index: 502770 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8319. Min Act: -0.1700
Data Index: 7252268 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3944. Min Range: -6.3944
Max Act: 5.8006. Min Act: -0.1700
Data Index: 3254741 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19