Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.9550. Min Act: -0.1700
Data Index: 5377272 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.7675. Min Act: -0.1700
Data Index: 7975770 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.6425. Min Act: -0.1700
Data Index: 3002055 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.6737. Min Act: -0.1700
Data Index: 5957364 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.5175. Min Act: -0.1700
Data Index: 1200929 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.5175. Min Act: -0.1700
Data Index: 4944422 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.5487. Min Act: -0.1700
Data Index: 3891645 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.4550. Min Act: -0.1700
Data Index: 3141654 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.4237. Min Act: -0.1700
Data Index: 4648391 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.4237. Min Act: -0.1700
Data Index: 5804593 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.4237. Min Act: -0.1700
Data Index: 6762243 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.4237. Min Act: -0.1700
Data Index: 529960 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.4237. Min Act: -0.1700
Data Index: 6531967 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.4237. Min Act: -0.1700
Data Index: 2476621 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.3925. Min Act: -0.1700
Data Index: 7982069 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.4237. Min Act: -0.1700
Data Index: 5739503 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.3612. Min Act: -0.1700
Data Index: 7321387 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.3300. Min Act: -0.1700
Data Index: 2393980 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.3612. Min Act: -0.1700
Data Index: 8160480 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9550. Min Range: -6.9550
Max Act: 6.3300. Min Act: -0.1700
Data Index: 5781402 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19