Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1797 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.5283. Min Act: -0.1700
Data Index: 7898789 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4970. Min Act: -0.1700
Data Index: 884005 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4657. Min Act: -0.1700
Data Index: 3772900 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4657. Min Act: -0.1700
Data Index: 7784056 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4500. Min Act: -0.1700
Data Index: 5739734 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4657. Min Act: -0.1700
Data Index: 3042290 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4500. Min Act: -0.1700
Data Index: 3370604 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4343. Min Act: -0.1700
Data Index: 477276 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4030. Min Act: -0.1700
Data Index: 262561 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4030. Min Act: -0.1700
Data Index: 1975407 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.3873. Min Act: -0.1700
Data Index: 5295546 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4030. Min Act: -0.1700
Data Index: 3456532 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.3873. Min Act: -0.1700
Data Index: 3176958 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.4030. Min Act: -0.1700
Data Index: 4945124 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.3716. Min Act: -0.1700
Data Index: 4088518 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.3716. Min Act: -0.1700
Data Index: 1855674 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.3559. Min Act: -0.1700
Data Index: 4475237 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.3559. Min Act: -0.1700
Data Index: 4727722 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.3559. Min Act: -0.1700
Data Index: 6425854 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5283. Min Range: -3.5283
Max Act: 3.3402. Min Act: -0.1700
Data Index: 1823609 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19