Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0411. Min Range: -5.0411
Max Act: 5.0411. Min Act: -0.1700
Data Index: 3380227 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0411. Min Range: -5.0411
Max Act: 5.0411. Min Act: -0.1700
Data Index: 3563570 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0411. Min Range: -5.0411
Max Act: 5.0411. Min Act: -0.1700
Data Index: 6778605 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.9474. Min Act: -0.1700
Data Index: 762209 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.9161. Min Act: -0.1700
Data Index: 3523180 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.9161. Min Act: -0.1700
Data Index: 6810573 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.8849. Min Act: -0.1700
Data Index: 6362331 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.8849. Min Act: -0.1700
Data Index: 8357605 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.8536. Min Act: -0.1700
Data Index: 6447685 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.8536. Min Act: -0.1700
Data Index: 6512411 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.8224. Min Act: -0.1700
Data Index: 163339 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.8224. Min Act: -0.1700
Data Index: 4763970 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.7911. Min Act: -0.1700
Data Index: 7581704 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.7599. Min Act: -0.1700
Data Index: 4042915 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.7911. Min Act: -0.1700
Data Index: 7988438 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.7911. Min Act: -0.1700
Data Index: 1315015 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.7911. Min Act: -0.1700
Data Index: 3011625 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.7911. Min Act: -0.1700
Data Index: 6087552 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.7286. Min Act: -0.1700
Data Index: 2468763 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0411. Min Range: -5.0411
Max Act: 4.7286. Min Act: -0.1700
Data Index: 2138827 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19