Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.8482. Min Act: -0.1700
Data Index: 7985826 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.8325. Min Act: -0.1700
Data Index: 6599436 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.8325. Min Act: -0.1700
Data Index: 4548225 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.8482. Min Act: -0.1700
Data Index: 2378763 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.8325. Min Act: -0.1700
Data Index: 5774556 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.8013. Min Act: -0.1700
Data Index: 6594530 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.8169. Min Act: -0.1700
Data Index: 8750809 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.8013. Min Act: -0.1700
Data Index: 207738 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.7387. Min Act: -0.1700
Data Index: 3097950 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.7700. Min Act: -0.1700
Data Index: 997492 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.7543. Min Act: -0.1700
Data Index: 574356 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.7387. Min Act: -0.1700
Data Index: 3841466 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.7543. Min Act: -0.1700
Data Index: 539451 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.7387. Min Act: -0.1700
Data Index: 6620876 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.7231. Min Act: -0.1700
Data Index: 5654722 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.6918. Min Act: -0.1700
Data Index: 3013250 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.6918. Min Act: -0.1700
Data Index: 2469424 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.6761. Min Act: -0.1700
Data Index: 1383163 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.6605. Min Act: -0.1700
Data Index: 3002544 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8482. Min Range: -3.8482
Max Act: 3.6605. Min Act: -0.1700
Data Index: 5106905 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19