Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.6421. Min Act: -0.1700
Data Index: 1101654 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.6421. Min Act: -0.1700
Data Index: 8388598 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.3296. Min Act: -0.1700
Data Index: 5611418 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.2984. Min Act: -0.1700
Data Index: 8752797 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.2984. Min Act: -0.1700
Data Index: 5828367 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.2671. Min Act: -0.1700
Data Index: 6911078 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.2671. Min Act: -0.1700
Data Index: 3922212 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.2359. Min Act: -0.1700
Data Index: 7273735 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.1734. Min Act: -0.1700
Data Index: 3705264 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.1421. Min Act: -0.1700
Data Index: 3464207 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.0796. Min Act: -0.1700
Data Index: 2210507 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.1421. Min Act: -0.1700
Data Index: 3840712 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.1109. Min Act: -0.1700
Data Index: 3676489 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.0796. Min Act: -0.1700
Data Index: 5555913 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.0796. Min Act: -0.1700
Data Index: 7582880 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.1109. Min Act: -0.1700
Data Index: 5520794 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.0796. Min Act: -0.1700
Data Index: 6661386 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.0796. Min Act: -0.1700
Data Index: 8767165 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.0796. Min Act: -0.1700
Data Index: 3690890 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6421. Min Range: -6.6421
Max Act: 6.0484. Min Act: -0.1700
Data Index: 5565295 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19