Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2079 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1533. Min Range: -5.1533
Max Act: 5.1533. Min Act: -0.1700
Data Index: 3936790 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8408. Min Act: -0.1700
Data Index: 2877407 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8408. Min Act: -0.1700
Data Index: 269225 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.7783. Min Act: -0.1700
Data Index: 2544660 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.7158. Min Act: -0.1700
Data Index: 8651369 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.7158. Min Act: -0.1700
Data Index: 1879492 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.7158. Min Act: -0.1700
Data Index: 4863385 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6845. Min Act: -0.1700
Data Index: 6498178 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.7158. Min Act: -0.1700
Data Index: 6521263 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.7158. Min Act: -0.1700
Data Index: 609290 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6845. Min Act: -0.1700
Data Index: 8361213 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6845. Min Act: -0.1700
Data Index: 3865373 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6845. Min Act: -0.1700
Data Index: 4678964 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6533. Min Act: -0.1700
Data Index: 7332887 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6220. Min Act: -0.1700
Data Index: 6410129 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6220. Min Act: -0.1700
Data Index: 2167434 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6220. Min Act: -0.1700
Data Index: 2185136 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6220. Min Act: -0.1700
Data Index: 7689391 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.6220. Min Act: -0.1700
Data Index: 6839242 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.5595. Min Act: -0.1700
Data Index: 3872730 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19