Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6005 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.4350. Min Act: -0.1700
Data Index: 7443677 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.3412. Min Act: -0.1700
Data Index: 6751489 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2787. Min Act: -0.1700
Data Index: 4170197 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.3100. Min Act: -0.1700
Data Index: 3304830 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.3100. Min Act: -0.1700
Data Index: 4531612 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.3100. Min Act: -0.1700
Data Index: 3851497 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2475. Min Act: -0.1700
Data Index: 7839339 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2787. Min Act: -0.1700
Data Index: 5565188 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2787. Min Act: -0.1700
Data Index: 6193619 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2475. Min Act: -0.1700
Data Index: 4015513 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2787. Min Act: -0.1700
Data Index: 3462499 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2787. Min Act: -0.1700
Data Index: 7672692 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2475. Min Act: -0.1700
Data Index: 5513954 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2475. Min Act: -0.1700
Data Index: 2021913 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2475. Min Act: -0.1700
Data Index: 3075103 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2475. Min Act: -0.1700
Data Index: 3389523 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2475. Min Act: -0.1700
Data Index: 6160337 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2787. Min Act: -0.1700
Data Index: 1072301 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2162. Min Act: -0.1700
Data Index: 7669031 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4350. Min Range: -5.4350
Max Act: 5.2162. Min Act: -0.1700
Data Index: 2115681 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19