Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 608 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.8624. Min Act: -0.1700
Data Index: 711366 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.8312. Min Act: -0.1700
Data Index: 7302191 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.7999. Min Act: -0.1700
Data Index: 485524 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.7999. Min Act: -0.1700
Data Index: 3306773 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.7374. Min Act: -0.1700
Data Index: 4311056 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.7374. Min Act: -0.1700
Data Index: 4403685 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.7062. Min Act: -0.1700
Data Index: 2340130 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.7062. Min Act: -0.1700
Data Index: 3257132 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6749. Min Act: -0.1700
Data Index: 2857910 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6749. Min Act: -0.1700
Data Index: 7589888 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6749. Min Act: -0.1700
Data Index: 2788200 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6749. Min Act: -0.1700
Data Index: 6562107 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6749. Min Act: -0.1700
Data Index: 5637334 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6437. Min Act: -0.1700
Data Index: 7964255 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6437. Min Act: -0.1700
Data Index: 3708708 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6437. Min Act: -0.1700
Data Index: 3902943 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6124. Min Act: -0.1700
Data Index: 7290775 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.6124. Min Act: -0.1700
Data Index: 7154503 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.5812. Min Act: -0.1700
Data Index: 3472267 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8624. Min Range: -6.8624
Max Act: 6.5812. Min Act: -0.1700
Data Index: 5160329 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19