Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 397 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.6113. Min Act: -0.1700
Data Index: 6144166 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.5488. Min Act: -0.1700
Data Index: 3854390 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.5488. Min Act: -0.1700
Data Index: 8212443 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.5488. Min Act: -0.1700
Data Index: 4652398 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.4238. Min Act: -0.1700
Data Index: 3041599 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.4550. Min Act: -0.1700
Data Index: 746739 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3925. Min Act: -0.1700
Data Index: 2056200 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 3899185 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 8536554 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 5249175 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 7891914 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 1876830 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 8295694 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 8643815 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 8177793 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.2988. Min Act: -0.1700
Data Index: 6993314 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 5539607 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 2102192 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 4891535 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 5051854 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19