Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.5377. Min Act: -0.1700
Data Index: 3739889 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.5690. Min Act: -0.1700
Data Index: 7019239 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.4127. Min Act: -0.1700
Data Index: 6095082 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.4127. Min Act: -0.1700
Data Index: 2786467 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.3502. Min Act: -0.1700
Data Index: 4880395 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.3190. Min Act: -0.1700
Data Index: 1376808 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.3190. Min Act: -0.1700
Data Index: 3749650 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.2877. Min Act: -0.1700
Data Index: 6281126 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.2565. Min Act: -0.1700
Data Index: 1263328 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.2252. Min Act: -0.1700
Data Index: 6795220 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.2252. Min Act: -0.1700
Data Index: 4966311 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.2252. Min Act: -0.1700
Data Index: 339873 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.1315. Min Act: -0.1700
Data Index: 4744195 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.1315. Min Act: -0.1700
Data Index: 8287177 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.1315. Min Act: -0.1700
Data Index: 7933411 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.1002. Min Act: -0.1700
Data Index: 2395805 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.0690. Min Act: -0.1700
Data Index: 3587086 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.0690. Min Act: -0.1700
Data Index: 7719409 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.0377. Min Act: -0.1700
Data Index: 2038996 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5690. Min Range: -6.5690
Max Act: 6.0377. Min Act: -0.1700
Data Index: 7761493 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19