Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1636. Min Range: -10.1636
Max Act: 10.1636. Min Act: -0.1700
Data Index: 8083170 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.6011. Min Act: -0.1700
Data Index: 6304579 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.5386. Min Act: -0.1700
Data Index: 3432520 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.4761. Min Act: -0.1700
Data Index: 531653 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.4136. Min Act: -0.1700
Data Index: 494041 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.2886. Min Act: -0.1700
Data Index: 5853311 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.2886. Min Act: -0.1700
Data Index: 2557649 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.2261. Min Act: -0.1700
Data Index: 489174 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.1011. Min Act: -0.1700
Data Index: 2700262 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.1636. Min Act: -0.1700
Data Index: 3931066 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.1011. Min Act: -0.1700
Data Index: 6454243 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.1011. Min Act: -0.1700
Data Index: 3407845 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.1011. Min Act: -0.1700
Data Index: 1362521 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.0386. Min Act: -0.1700
Data Index: 867664 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.0386. Min Act: -0.1700
Data Index: 4421731 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.0386. Min Act: -0.1700
Data Index: 1108281 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1636. Min Range: -10.1636
Max Act: 9.0386. Min Act: -0.1700
Data Index: 5123510 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1636. Min Range: -10.1636
Max Act: 8.9136. Min Act: -0.1700
Data Index: 5383243 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1636. Min Range: -10.1636
Max Act: 8.9136. Min Act: -0.1700
Data Index: 1164179 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1636. Min Range: -10.1636
Max Act: 8.9761. Min Act: -0.1700
Data Index: 145498 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19