Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.4396. Min Act: -0.1700
Data Index: 3052228 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.3459. Min Act: -0.1700
Data Index: 8581988 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.3146. Min Act: -0.1700
Data Index: 2622267 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.2834. Min Act: -0.1700
Data Index: 3843254 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.1896. Min Act: -0.1700
Data Index: 2141126 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.1584. Min Act: -0.1700
Data Index: 6207312 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.1584. Min Act: -0.1700
Data Index: 2000619 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.1271. Min Act: -0.1700
Data Index: 5196958 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.1271. Min Act: -0.1700
Data Index: 6010788 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0959. Min Act: -0.1700
Data Index: 4518471 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0959. Min Act: -0.1700
Data Index: 445865 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0959. Min Act: -0.1700
Data Index: 3068157 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0959. Min Act: -0.1700
Data Index: 5717504 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.1271. Min Act: -0.1700
Data Index: 7333187 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0959. Min Act: -0.1700
Data Index: 6145515 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0646. Min Act: -0.1700
Data Index: 4993403 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0646. Min Act: -0.1700
Data Index: 3116013 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0646. Min Act: -0.1700
Data Index: 4704446 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0334. Min Act: -0.1700
Data Index: 3358800 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4396. Min Range: -6.4396
Max Act: 6.0334. Min Act: -0.1700
Data Index: 1748475 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19