Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5088 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.4694. Min Act: -0.1700
Data Index: 6862363 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.4069. Min Act: -0.1700
Data Index: 5846234 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.3756. Min Act: -0.1700
Data Index: 1131957 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.3756. Min Act: -0.1700
Data Index: 949813 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.3444. Min Act: -0.1700
Data Index: 4525539 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.3131. Min Act: -0.1700
Data Index: 2010199 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.3444. Min Act: -0.1700
Data Index: 7088790 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.2506. Min Act: -0.1700
Data Index: 6304572 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.2506. Min Act: -0.1700
Data Index: 2261252 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.2506. Min Act: -0.1700
Data Index: 8679550 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.2194. Min Act: -0.1700
Data Index: 2339905 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.2194. Min Act: -0.1700
Data Index: 7007127 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.1881. Min Act: -0.1700
Data Index: 6657984 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.1881. Min Act: -0.1700
Data Index: 276741 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.1881. Min Act: -0.1700
Data Index: 2464779 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.1881. Min Act: -0.1700
Data Index: 8063785 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.1881. Min Act: -0.1699
Data Index: 4081382 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.1881. Min Act: -0.1700
Data Index: 3955630 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.1569. Min Act: -0.1700
Data Index: 1461079 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4694. Min Range: -6.4694
Max Act: 6.1569. Min Act: -0.1700
Data Index: 6789105 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19