Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0806. Min Range: -6.0806
Max Act: 6.0806. Min Act: -0.1700
Data Index: 5080130 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0806. Min Range: -6.0806
Max Act: 6.0493. Min Act: -0.1700
Data Index: 8197827 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0806. Min Range: -6.0806
Max Act: 6.0493. Min Act: -0.1700
Data Index: 2152440 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.9868. Min Act: -0.1700
Data Index: 4924233 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.8931. Min Act: -0.1700
Data Index: 803122 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.8931. Min Act: -0.1700
Data Index: 7801392 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.8618. Min Act: -0.1700
Data Index: 4277681 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7681. Min Act: -0.1700
Data Index: 2150770 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7993. Min Act: -0.1700
Data Index: 2735049 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7681. Min Act: -0.1700
Data Index: 1052449 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7993. Min Act: -0.1700
Data Index: 2554964 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7681. Min Act: -0.1700
Data Index: 4113048 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7368. Min Act: -0.1700
Data Index: 7666479 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7056. Min Act: -0.1700
Data Index: 5162588 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7056. Min Act: -0.1700
Data Index: 8048056 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7056. Min Act: -0.1700
Data Index: 209801 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7056. Min Act: -0.1700
Data Index: 7150688 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.7056. Min Act: -0.1700
Data Index: 5619521 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.6743. Min Act: -0.1700
Data Index: 8160039 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0806. Min Range: -6.0806
Max Act: 5.6743. Min Act: -0.1700
Data Index: 6623371 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19