Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1622. Min Range: -4.1622
Max Act: 4.1622. Min Act: -0.1700
Data Index: 4691918 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1622. Min Range: -4.1622
Max Act: 4.0059. Min Act: -0.1700
Data Index: 1645483 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1622. Min Range: -4.1622
Max Act: 4.0059. Min Act: -0.1700
Data Index: 4420318 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1622. Min Range: -4.1622
Max Act: 4.0059. Min Act: -0.1700
Data Index: 5850972 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1622. Min Range: -4.1622
Max Act: 4.0059. Min Act: -0.1700
Data Index: 5863517 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1622. Min Range: -4.1622
Max Act: 4.0059. Min Act: -0.1700
Data Index: 56248 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9746. Min Act: -0.1700
Data Index: 4496704 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9746. Min Act: -0.1700
Data Index: 6979014 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9746. Min Act: -0.1700
Data Index: 2015737 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9746. Min Act: -0.1700
Data Index: 6534485 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9433. Min Act: -0.1700
Data Index: 6912870 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9433. Min Act: -0.1700
Data Index: 6600900 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9433. Min Act: -0.1700
Data Index: 5284174 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9433. Min Act: -0.1700
Data Index: 2620844 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9433. Min Act: -0.1700
Data Index: 4503515 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9121. Min Act: -0.1700
Data Index: 5035706 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9121. Min Act: -0.1700
Data Index: 4921129 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9121. Min Act: -0.1700
Data Index: 6033842 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9121. Min Act: -0.1700
Data Index: 2392848 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1622. Min Range: -4.1622
Max Act: 3.9121. Min Act: -0.1700
Data Index: 3188582 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19