Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1516. Min Range: -8.1516
Max Act: 8.1516. Min Act: -0.1700
Data Index: 1599410 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1516. Min Range: -8.1516
Max Act: 8.0266. Min Act: -0.1700
Data Index: 2356769 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.8703. Min Act: -0.1700
Data Index: 276901 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.8391. Min Act: -0.1700
Data Index: 2694938 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.7453. Min Act: -0.1700
Data Index: 2833722 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.7453. Min Act: -0.1700
Data Index: 6513661 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.7453. Min Act: -0.1700
Data Index: 815587 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.7453. Min Act: -0.1700
Data Index: 4026234 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.7141. Min Act: -0.1700
Data Index: 7786401 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.6828. Min Act: -0.1700
Data Index: 8392640 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.6828. Min Act: -0.1700
Data Index: 3290030 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.6516. Min Act: -0.1700
Data Index: 2511061 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.6516. Min Act: -0.1700
Data Index: 5968276 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.5891. Min Act: -0.1700
Data Index: 3714591 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.5891. Min Act: -0.1700
Data Index: 3542241 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.5578. Min Act: -0.1700
Data Index: 2487587 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.5891. Min Act: -0.1700
Data Index: 259212 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.4953. Min Act: -0.1700
Data Index: 7524384 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.4953. Min Act: -0.1700
Data Index: 6719242 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1516. Min Range: -8.1516
Max Act: 7.4641. Min Act: -0.1700
Data Index: 6027747 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19