Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4854 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.6405. Min Act: -0.1700
Data Index: 3941880 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.5155. Min Act: -0.1700
Data Index: 3302256 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.5155. Min Act: -0.1700
Data Index: 6739430 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3905. Min Act: -0.1700
Data Index: 5163330 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3905. Min Act: -0.1700
Data Index: 3781500 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3905. Min Act: -0.1700
Data Index: 3565577 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3593. Min Act: -0.1700
Data Index: 992521 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3905. Min Act: -0.1700
Data Index: 6658701 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.3280. Min Act: -0.1700
Data Index: 1207543 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.2655. Min Act: -0.1700
Data Index: 5594107 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.2343. Min Act: -0.1700
Data Index: 6706605 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1718. Min Act: -0.1700
Data Index: 5327895 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1405. Min Act: -0.1700
Data Index: 8477285 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1405. Min Act: -0.1700
Data Index: 8260316 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1093. Min Act: -0.1700
Data Index: 8033756 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1093. Min Act: -0.1700
Data Index: 3605163 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1405. Min Act: -0.1700
Data Index: 6054216 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.1093. Min Act: -0.1700
Data Index: 190240 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.0780. Min Act: -0.1700
Data Index: 589462 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6405. Min Range: -6.6405
Max Act: 6.0780. Min Act: -0.1700
Data Index: 4081494 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19