Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.5768. Min Act: -0.1700
Data Index: 7969454 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.3581. Min Act: -0.1700
Data Index: 1196264 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.3268. Min Act: -0.1700
Data Index: 5934136 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.2331. Min Act: -0.1700
Data Index: 2167150 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.2331. Min Act: -0.1700
Data Index: 2399120 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.2018. Min Act: -0.1700
Data Index: 1734261 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.2331. Min Act: -0.1700
Data Index: 7317001 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.1706. Min Act: -0.1700
Data Index: 5383329 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.1706. Min Act: -0.1700
Data Index: 4757985 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.1706. Min Act: -0.1700
Data Index: 4996962 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.1706. Min Act: -0.1700
Data Index: 5289907 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.1393. Min Act: -0.1700
Data Index: 7489931 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.1393. Min Act: -0.1700
Data Index: 5749035 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.0768. Min Act: -0.1700
Data Index: 3707949 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.1081. Min Act: -0.1700
Data Index: 494475 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.0768. Min Act: -0.1700
Data Index: 1882352 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.0768. Min Act: -0.1700
Data Index: 4247123 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.0768. Min Act: -0.1700
Data Index: 1610189 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.0768. Min Act: -0.1700
Data Index: 6578228 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5768. Min Range: -5.5768
Max Act: 5.1081. Min Act: -0.1700
Data Index: 5387915 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19