Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 172 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.1621. Min Act: -0.1700
Data Index: 8182117 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0996. Min Act: -0.1700
Data Index: 1165744 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0996. Min Act: -0.1700
Data Index: 2949538 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0996. Min Act: -0.1700
Data Index: 3391887 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0684. Min Act: -0.1700
Data Index: 3199514 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0684. Min Act: -0.1700
Data Index: 3434468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0371. Min Act: -0.1700
Data Index: 4201749 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0059. Min Act: -0.1700
Data Index: 5229247 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0059. Min Act: -0.1700
Data Index: 3825655 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0059. Min Act: -0.1700
Data Index: 2434822 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0059. Min Act: -0.1700
Data Index: 6853522 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1621. Min Range: -4.1621
Max Act: 3.9746. Min Act: -0.1700
Data Index: 7420144 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1621. Min Range: -4.1621
Max Act: 3.9746. Min Act: -0.1700
Data Index: 7299827 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1621. Min Range: -4.1621
Max Act: 3.9746. Min Act: -0.1700
Data Index: 6215765 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1621. Min Range: -4.1621
Max Act: 4.0059. Min Act: -0.1700
Data Index: 4128804 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1621. Min Range: -4.1621
Max Act: 3.9746. Min Act: -0.1700
Data Index: 652520 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1621. Min Range: -4.1621
Max Act: 3.9121. Min Act: -0.1700
Data Index: 7811327 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1621. Min Range: -4.1621
Max Act: 3.9121. Min Act: -0.1700
Data Index: 4028210 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1621. Min Range: -4.1621
Max Act: 3.9121. Min Act: -0.1700
Data Index: 7345638 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1621. Min Range: -4.1621
Max Act: 3.9121. Min Act: -0.1700
Data Index: 2190011 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19