Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.8738. Min Act: -0.1700
Data Index: 6837961 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4988. Min Act: -0.1700
Data Index: 470922 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4988. Min Act: -0.1700
Data Index: 2529712 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4675. Min Act: -0.1700
Data Index: 1284697 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4988. Min Act: -0.1700
Data Index: 1047632 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4675. Min Act: -0.1700
Data Index: 129615 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4363. Min Act: -0.1700
Data Index: 4788248 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4050. Min Act: -0.1700
Data Index: 241683 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4050. Min Act: -0.1700
Data Index: 1033546 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.4363. Min Act: -0.1700
Data Index: 3070903 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3738. Min Act: -0.1700
Data Index: 5576544 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3738. Min Act: -0.1700
Data Index: 59478 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3425. Min Act: -0.1700
Data Index: 3385892 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3425. Min Act: -0.1700
Data Index: 7014948 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3425. Min Act: -0.1700
Data Index: 6930567 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3425. Min Act: -0.1700
Data Index: 8822562 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3425. Min Act: -0.1700
Data Index: 8322168 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3738. Min Act: -0.1700
Data Index: 845358 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.3113. Min Act: -0.1700
Data Index: 5418587 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8738. Min Range: -5.8738
Max Act: 5.2800. Min Act: -0.1700
Data Index: 5156688 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19