Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2693 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.4806. Min Act: -0.1700
Data Index: 886699 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.3243. Min Act: -0.1700
Data Index: 4528988 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.2931. Min Act: -0.1700
Data Index: 1487559 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.2618. Min Act: -0.1700
Data Index: 2489958 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.1993. Min Act: -0.1700
Data Index: 8583442 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.1368. Min Act: -0.1700
Data Index: 6333577 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.1368. Min Act: -0.1700
Data Index: 3570227 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.0743. Min Act: -0.1700
Data Index: 86493 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.0743. Min Act: -0.1700
Data Index: 3040497 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.0743. Min Act: -0.1700
Data Index: 6003233 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.0743. Min Act: -0.1700
Data Index: 6041321 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.0431. Min Act: -0.1700
Data Index: 155559 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4806. Min Range: -5.4806
Max Act: 5.0118. Min Act: -0.1700
Data Index: 6473996 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4806. Min Range: -5.4806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 648836 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4806. Min Range: -5.4806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 4750739 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4806. Min Range: -5.4806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 8510413 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4806. Min Range: -5.4806
Max Act: 4.9806. Min Act: -0.1700
Data Index: 785357 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4806. Min Range: -5.4806
Max Act: 4.9493. Min Act: -0.1700
Data Index: 7471324 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4806. Min Range: -5.4806
Max Act: 4.9493. Min Act: -0.1700
Data Index: 3130195 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4806. Min Range: -5.4806
Max Act: 4.9493. Min Act: -0.1700
Data Index: 4689037 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19