Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5068 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.8937. Min Act: -0.1700
Data Index: 4355238 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.5187. Min Act: -0.1700
Data Index: 4967488 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.5812. Min Act: -0.1700
Data Index: 6181895 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.5812. Min Act: -0.1700
Data Index: 317175 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.5187. Min Act: -0.1700
Data Index: 3832722 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.5187. Min Act: -0.1700
Data Index: 3111775 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.5187. Min Act: -0.1700
Data Index: 221927 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.4562. Min Act: -0.1700
Data Index: 3111773 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3937. Min Act: -0.1700
Data Index: 8763890 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3937. Min Act: -0.1700
Data Index: 4678300 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3937. Min Act: -0.1700
Data Index: 1423067 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3312. Min Act: -0.1700
Data Index: 7342111 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3937. Min Act: -0.1700
Data Index: 6181899 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3937. Min Act: -0.1700
Data Index: 1935581 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3312. Min Act: -0.1700
Data Index: 6754345 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3312. Min Act: -0.1700
Data Index: 5879846 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3312. Min Act: -0.1700
Data Index: 7510858 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3312. Min Act: -0.1700
Data Index: 7527766 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3312. Min Act: -0.1700
Data Index: 3954397 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8937. Min Range: -9.8937
Max Act: 9.3312. Min Act: -0.1700
Data Index: 5458928 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19