Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0116. Min Range: -5.0116
Max Act: 5.0116. Min Act: -0.1700
Data Index: 8055570 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0116. Min Range: -5.0116
Max Act: 5.0116. Min Act: -0.1700
Data Index: 74973 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0116. Min Range: -5.0116
Max Act: 5.0116. Min Act: -0.1700
Data Index: 6383906 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.9803. Min Act: -0.1700
Data Index: 7406018 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.9803. Min Act: -0.1700
Data Index: 549598 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.9491. Min Act: -0.1700
Data Index: 4739051 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.9178. Min Act: -0.1700
Data Index: 8259057 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.9178. Min Act: -0.1700
Data Index: 3015608 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8866. Min Act: -0.1700
Data Index: 2165751 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8866. Min Act: -0.1700
Data Index: 7967548 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8553. Min Act: -0.1700
Data Index: 5617399 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8241. Min Act: -0.1700
Data Index: 7665563 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8553. Min Act: -0.1700
Data Index: 1862873 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7928. Min Act: -0.1700
Data Index: 5089158 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7928. Min Act: -0.1700
Data Index: 828457 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.8241. Min Act: -0.1700
Data Index: 2765499 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7928. Min Act: -0.1700
Data Index: 1437578 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7928. Min Act: -0.1700
Data Index: 2342492 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7928. Min Act: -0.1700
Data Index: 1309288 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0116. Min Range: -5.0116
Max Act: 4.7616. Min Act: -0.1700
Data Index: 7947347 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19