Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.1300. Min Act: -0.1700
Data Index: 7100277 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0987. Min Act: -0.1700
Data Index: 7953422 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0675. Min Act: -0.1700
Data Index: 7907173 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0987. Min Act: -0.1700
Data Index: 5471047 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0987. Min Act: -0.1700
Data Index: 2732893 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0362. Min Act: -0.1700
Data Index: 4079436 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0362. Min Act: -0.1700
Data Index: 1418485 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0049. Min Act: -0.1700
Data Index: 4654929 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0049. Min Act: -0.1700
Data Index: 2733329 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.9737. Min Act: -0.1700
Data Index: 5450574 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0049. Min Act: -0.1700
Data Index: 7256154 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.9737. Min Act: -0.1700
Data Index: 4249443 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.9737. Min Act: -0.1700
Data Index: 4795555 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1300. Min Range: -4.1300
Max Act: 4.0049. Min Act: -0.1700
Data Index: 7080148 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.9737. Min Act: -0.1700
Data Index: 5939295 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.8799. Min Act: -0.1700
Data Index: 7626592 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.9112. Min Act: -0.1700
Data Index: 5533171 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.9424. Min Act: -0.1700
Data Index: 4737710 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.9424. Min Act: -0.1700
Data Index: 2405668 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1300. Min Range: -4.1300
Max Act: 3.9424. Min Act: -0.1700
Data Index: 377946 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19