Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2487 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0735. Min Range: -10.0735
Max Act: 10.0735. Min Act: -0.1700
Data Index: 5655875 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0735. Min Range: -10.0735
Max Act: 9.5735. Min Act: -0.1700
Data Index: 6745875 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0735. Min Range: -10.0735
Max Act: 9.2610. Min Act: -0.1700
Data Index: 303324 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0735. Min Range: -10.0735
Max Act: 9.2610. Min Act: -0.1700
Data Index: 1968527 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0735. Min Range: -10.0735
Max Act: 9.1985. Min Act: -0.1700
Data Index: 6275193 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0735. Min Range: -10.0735
Max Act: 9.1985. Min Act: -0.1700
Data Index: 1705340 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0735. Min Range: -10.0735
Max Act: 9.0735. Min Act: -0.1700
Data Index: 8145362 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0735. Min Range: -10.0735
Max Act: 9.0110. Min Act: -0.1700
Data Index: 5637825 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0735. Min Range: -10.0735
Max Act: 9.0110. Min Act: -0.1700
Data Index: 8474936 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.9485. Min Act: -0.1700
Data Index: 6689825 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.9485. Min Act: -0.1700
Data Index: 2646413 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.8860. Min Act: -0.1700
Data Index: 6244709 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.9485. Min Act: -0.1700
Data Index: 765611 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.9485. Min Act: -0.1700
Data Index: 8759980 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.9485. Min Act: -0.1700
Data Index: 5205771 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.8860. Min Act: -0.1700
Data Index: 2519802 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.8235. Min Act: -0.1700
Data Index: 2742446 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.8235. Min Act: -0.1700
Data Index: 6687496 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.8235. Min Act: -0.1700
Data Index: 2388362 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0735. Min Range: -10.0735
Max Act: 8.8235. Min Act: -0.1700
Data Index: 807771 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19