Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.8635. Min Act: -0.1700
Data Index: 7282966 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.8010. Min Act: -0.1700
Data Index: 7757826 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.7072. Min Act: -0.1700
Data Index: 7282963 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.6135. Min Act: -0.1700
Data Index: 5891687 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.6447. Min Act: -0.1700
Data Index: 7856418 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.6135. Min Act: -0.1700
Data Index: 7282964 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.5822. Min Act: -0.1700
Data Index: 1232521 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.5822. Min Act: -0.1700
Data Index: 4562907 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.5822. Min Act: -0.1700
Data Index: 7282961 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.5510. Min Act: -0.1700
Data Index: 7282962 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.5197. Min Act: -0.1700
Data Index: 6462769 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.4572. Min Act: -0.1700
Data Index: 3372056 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.4572. Min Act: -0.1700
Data Index: 8831066 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.4572. Min Act: -0.1700
Data Index: 7312835 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.3947. Min Act: -0.1700
Data Index: 6905668 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.3947. Min Act: -0.1700
Data Index: 5450231 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.3947. Min Act: -0.1700
Data Index: 5731319 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.3947. Min Act: -0.1700
Data Index: 4003959 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.3947. Min Act: -0.1700
Data Index: 3371199 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8635. Min Range: -5.8635
Max Act: 5.3635. Min Act: -0.1700
Data Index: 5868224 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19