Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3663 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.5264. Min Act: -0.1700
Data Index: 5757795 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.5264. Min Act: -0.1700
Data Index: 6176448 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.4639. Min Act: -0.1700
Data Index: 8654838 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.4327. Min Act: -0.1700
Data Index: 4445486 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.3389. Min Act: -0.1700
Data Index: 1752347 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.2764. Min Act: -0.1700
Data Index: 8278324 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.1514. Min Act: -0.1700
Data Index: 7250995 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.1202. Min Act: -0.1700
Data Index: 6477935 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.1202. Min Act: -0.1700
Data Index: 5419449 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.1202. Min Act: -0.1700
Data Index: 220542 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.0889. Min Act: -0.1700
Data Index: 4801174 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.0577. Min Act: -0.1700
Data Index: 6257572 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.0577. Min Act: -0.1700
Data Index: 3840508 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.0577. Min Act: -0.1700
Data Index: 3205785 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5264. Min Range: -6.5264
Max Act: 6.0264. Min Act: -0.1700
Data Index: 113177 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5264. Min Range: -6.5264
Max Act: 5.9952. Min Act: -0.1700
Data Index: 6682358 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5264. Min Range: -6.5264
Max Act: 5.9952. Min Act: -0.1700
Data Index: 8277152 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5264. Min Range: -6.5264
Max Act: 5.9639. Min Act: -0.1700
Data Index: 3839799 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5264. Min Range: -6.5264
Max Act: 5.9639. Min Act: -0.1700
Data Index: 3226469 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5264. Min Range: -6.5264
Max Act: 5.9327. Min Act: -0.1700
Data Index: 6555701 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19