Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.8591. Min Act: -0.1700
Data Index: 4027231 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6716. Min Act: -0.1700
Data Index: 4985694 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.5778. Min Act: -0.1700
Data Index: 7214137 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.4841. Min Act: -0.1700
Data Index: 5512647 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.4528. Min Act: -0.1700
Data Index: 7538869 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.4216. Min Act: -0.1700
Data Index: 2327270 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3903. Min Act: -0.1700
Data Index: 4765727 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3591. Min Act: -0.1700
Data Index: 2649845 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3278. Min Act: -0.1700
Data Index: 8130862 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3591. Min Act: -0.1700
Data Index: 4100048 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3591. Min Act: -0.1700
Data Index: 2807154 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3591. Min Act: -0.1700
Data Index: 5678371 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3591. Min Act: -0.1700
Data Index: 3316650 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 8639961 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.3278. Min Act: -0.1700
Data Index: 6416216 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 5923096 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 1930955 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 5942602 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2966. Min Act: -0.1700
Data Index: 582493 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.2653. Min Act: -0.1700
Data Index: 3133117 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19