Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3244 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.6421. Min Act: -0.1700
Data Index: 6238164 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.3608. Min Act: -0.1700
Data Index: 3936594 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2358. Min Act: -0.1700
Data Index: 762808 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2358. Min Act: -0.1700
Data Index: 2985303 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.1420. Min Act: -0.1700
Data Index: 7439000 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0795. Min Act: -0.1700
Data Index: 2878177 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.1108. Min Act: -0.1700
Data Index: 6049534 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.1108. Min Act: -0.1700
Data Index: 7685611 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0795. Min Act: -0.1700
Data Index: 8185999 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0795. Min Act: -0.1700
Data Index: 1224478 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0795. Min Act: -0.1700
Data Index: 6163384 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0483. Min Act: -0.1700
Data Index: 7252222 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0483. Min Act: -0.1700
Data Index: 2607150 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0483. Min Act: -0.1700
Data Index: 5136396 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0170. Min Act: -0.1700
Data Index: 4294930 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0170. Min Act: -0.1700
Data Index: 8716285 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0483. Min Act: -0.1700
Data Index: 5671959 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.0170. Min Act: -0.1700
Data Index: 2848538 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6421. Min Range: -4.6421
Max Act: 3.9857. Min Act: -0.1700
Data Index: 2861215 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6421. Min Range: -4.6421
Max Act: 3.9857. Min Act: -0.1700
Data Index: 4308842 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19