Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1813 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1358. Min Range: -7.1358
Max Act: 7.1358. Min Act: -0.1700
Data Index: 1889198 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1358. Min Range: -7.1358
Max Act: 7.0420. Min Act: -0.1700
Data Index: 2588454 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.9795. Min Act: -0.1700
Data Index: 5347907 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.8233. Min Act: -0.1700
Data Index: 5253317 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.8233. Min Act: -0.1700
Data Index: 3368367 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.7920. Min Act: -0.1700
Data Index: 6019700 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.7920. Min Act: -0.1700
Data Index: 4370332 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.7295. Min Act: -0.1700
Data Index: 1010930 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.7295. Min Act: -0.1700
Data Index: 6335536 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6983. Min Act: -0.1700
Data Index: 3432850 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6983. Min Act: -0.1700
Data Index: 5711597 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6983. Min Act: -0.1700
Data Index: 8810123 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6670. Min Act: -0.1700
Data Index: 3356215 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6670. Min Act: -0.1700
Data Index: 5278462 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6358. Min Act: -0.1700
Data Index: 491213 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6670. Min Act: -0.1700
Data Index: 8820710 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6358. Min Act: -0.1700
Data Index: 89245 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6358. Min Act: -0.1700
Data Index: 1987590 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6358. Min Act: -0.1700
Data Index: 6713916 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1358. Min Range: -7.1358
Max Act: 6.6358. Min Act: -0.1700
Data Index: 3589670 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19