Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.5857. Min Act: -0.1700
Data Index: 153052 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2732. Min Act: -0.1700
Data Index: 153050 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.3044. Min Act: -0.1700
Data Index: 2854707 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2419. Min Act: -0.1700
Data Index: 8244203 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2732. Min Act: -0.1700
Data Index: 4692779 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2732. Min Act: -0.1700
Data Index: 583863 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.2732. Min Act: -0.1700
Data Index: 3905953 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1794. Min Act: -0.1700
Data Index: 153055 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 154296 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 5494444 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 4706126 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 831552 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.1169. Min Act: -0.1700
Data Index: 8509878 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0544. Min Act: -0.1700
Data Index: 118213 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0857. Min Act: -0.1700
Data Index: 1206949 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0857. Min Act: -0.1700
Data Index: 4110104 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0544. Min Act: -0.1700
Data Index: 1232290 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0544. Min Act: -0.1700
Data Index: 2426686 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0544. Min Act: -0.1700
Data Index: 6347957 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5857. Min Range: -6.5857
Max Act: 6.0544. Min Act: -0.1700
Data Index: 2395943 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19