Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5338 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.9487. Min Act: -0.1700
Data Index: 4008413 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.9799. Min Act: -0.1700
Data Index: 7622439 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.9799. Min Act: -0.1700
Data Index: 4462435 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.8862. Min Act: -0.1700
Data Index: 7007268 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.8549. Min Act: -0.1700
Data Index: 8229936 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.7924. Min Act: -0.1700
Data Index: 6541457 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.7612. Min Act: -0.1700
Data Index: 3859422 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.7299. Min Act: -0.1700
Data Index: 4262842 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.6362. Min Act: -0.1700
Data Index: 3171429 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.6674. Min Act: -0.1700
Data Index: 3375919 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.6674. Min Act: -0.1700
Data Index: 2383011 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.6674. Min Act: -0.1700
Data Index: 2200265 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.6362. Min Act: -0.1700
Data Index: 1056580 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.6362. Min Act: -0.1700
Data Index: 5083532 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.5737. Min Act: -0.1700
Data Index: 3662071 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.6049. Min Act: -0.1700
Data Index: 6751422 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.5737. Min Act: -0.1700
Data Index: 1541472 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.5424. Min Act: -0.1700
Data Index: 7933725 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.5424. Min Act: -0.1700
Data Index: 571249 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9799. Min Range: -5.9799
Max Act: 5.5424. Min Act: -0.1700
Data Index: 3836356 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19