Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1651 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.5563. Min Act: -0.1700
Data Index: 141063 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.4938. Min Act: -0.1700
Data Index: 2346656 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.4313. Min Act: -0.1700
Data Index: 1261766 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.4000. Min Act: -0.1700
Data Index: 7248117 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.4000. Min Act: -0.1700
Data Index: 5933238 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.4000. Min Act: -0.1700
Data Index: 5082414 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.3688. Min Act: -0.1700
Data Index: 6711696 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.3688. Min Act: -0.1700
Data Index: 2357464 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.3375. Min Act: -0.1700
Data Index: 6065997 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.3375. Min Act: -0.1700
Data Index: 5254208 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.3375. Min Act: -0.1700
Data Index: 5254209 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.3063. Min Act: -0.1700
Data Index: 8085962 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.3063. Min Act: -0.1700
Data Index: 2016483 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.2750. Min Act: -0.1700
Data Index: 4944793 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.2438. Min Act: -0.1700
Data Index: 1906807 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.2750. Min Act: -0.1700
Data Index: 4005111 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.2750. Min Act: -0.1700
Data Index: 6913459 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.2438. Min Act: -0.1700
Data Index: 3840771 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.2438. Min Act: -0.1700
Data Index: 1159012 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5563. Min Range: -4.5563
Max Act: 4.2438. Min Act: -0.1700
Data Index: 265645 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19