Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1407. Min Range: -5.1407
Max Act: 5.1407. Min Act: -0.1700
Data Index: 3114544 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.9532. Min Act: -0.1700
Data Index: 1759009 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.9220. Min Act: -0.1700
Data Index: 6236309 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.8907. Min Act: -0.1700
Data Index: 5841835 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.8907. Min Act: -0.1700
Data Index: 1273377 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.8595. Min Act: -0.1700
Data Index: 2989248 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.8282. Min Act: -0.1700
Data Index: 3401650 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.8282. Min Act: -0.1700
Data Index: 3769135 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.8282. Min Act: -0.1700
Data Index: 1180043 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7970. Min Act: -0.1700
Data Index: 7066608 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7657. Min Act: -0.1700
Data Index: 7669436 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7970. Min Act: -0.1700
Data Index: 3601211 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7657. Min Act: -0.1700
Data Index: 4359520 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7970. Min Act: -0.1700
Data Index: 5925161 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7345. Min Act: -0.1700
Data Index: 1911274 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7345. Min Act: -0.1700
Data Index: 7859796 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7345. Min Act: -0.1700
Data Index: 4013349 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7345. Min Act: -0.1700
Data Index: 8182833 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7345. Min Act: -0.1700
Data Index: 8341161 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1407. Min Range: -5.1407
Max Act: 4.7657. Min Act: -0.1700
Data Index: 2333585 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19