Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1833 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.7675. Min Act: -0.1700
Data Index: 5726622 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.8300. Min Act: -0.1700
Data Index: 7598116 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.7675. Min Act: -0.1700
Data Index: 3144066 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.7675. Min Act: -0.1700
Data Index: 6243781 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.7675. Min Act: -0.1700
Data Index: 2539289 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.7363. Min Act: -0.1700
Data Index: 6545706 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.7050. Min Act: -0.1700
Data Index: 8218253 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.6738. Min Act: -0.1700
Data Index: 6574284 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.6425. Min Act: -0.1700
Data Index: 7055893 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.6425. Min Act: -0.1700
Data Index: 3767583 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.6425. Min Act: -0.1700
Data Index: 5189908 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.6113. Min Act: -0.1700
Data Index: 740060 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.6113. Min Act: -0.1700
Data Index: 8164360 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.6113. Min Act: -0.1700
Data Index: 6144906 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.5488. Min Act: -0.1700
Data Index: 511382 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.5800. Min Act: -0.1700
Data Index: 1119035 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.5488. Min Act: -0.1700
Data Index: 5221576 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.4863. Min Act: -0.1700
Data Index: 3882929 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.4863. Min Act: -0.1700
Data Index: 3669394 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8300. Min Range: -5.8300
Max Act: 5.5175. Min Act: -0.1700
Data Index: 1704596 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19