Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5141 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2420. Min Range: -9.2420
Max Act: 9.2420. Min Act: -0.1700
Data Index: 730267 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2420. Min Range: -9.2420
Max Act: 9.1170. Min Act: -0.1700
Data Index: 5353025 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2420. Min Range: -9.2420
Max Act: 9.1170. Min Act: -0.1700
Data Index: 167913 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2420. Min Range: -9.2420
Max Act: 9.0545. Min Act: -0.1700
Data Index: 7742541 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.9920. Min Act: -0.1700
Data Index: 4362384 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.9920. Min Act: -0.1700
Data Index: 151509 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.9295. Min Act: -0.1700
Data Index: 3495235 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.9920. Min Act: -0.1700
Data Index: 3577151 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.9295. Min Act: -0.1700
Data Index: 7114741 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.8045. Min Act: -0.1700
Data Index: 2562306 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.8045. Min Act: -0.1700
Data Index: 6336119 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.7420. Min Act: -0.1700
Data Index: 4066692 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.7420. Min Act: -0.1700
Data Index: 7206379 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.7420. Min Act: -0.1700
Data Index: 5577553 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.7420. Min Act: -0.1700
Data Index: 193742 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.6795. Min Act: -0.1700
Data Index: 4062201 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.6795. Min Act: -0.1700
Data Index: 4514620 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.6170. Min Act: -0.1700
Data Index: 5272987 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.6170. Min Act: -0.1700
Data Index: 2642753 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2420. Min Range: -9.2420
Max Act: 8.5545. Min Act: -0.1700
Data Index: 5184075 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19