Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1398 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.9416. Min Act: -0.1700
Data Index: 3606171 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.9260. Min Act: -0.1700
Data Index: 2787464 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8947. Min Act: -0.1700
Data Index: 8541673 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8947. Min Act: -0.1700
Data Index: 7523050 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8947. Min Act: -0.1700
Data Index: 4063074 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8634. Min Act: -0.1700
Data Index: 4935345 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8634. Min Act: -0.1700
Data Index: 1360306 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8634. Min Act: -0.1700
Data Index: 6090645 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8634. Min Act: -0.1700
Data Index: 403143 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8478. Min Act: -0.1700
Data Index: 4052752 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8478. Min Act: -0.1700
Data Index: 7933662 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8322. Min Act: -0.1700
Data Index: 2180334 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8322. Min Act: -0.1700
Data Index: 348925 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8322. Min Act: -0.1700
Data Index: 4866384 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8322. Min Act: -0.1700
Data Index: 8268555 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8009. Min Act: -0.1700
Data Index: 2342908 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8322. Min Act: -0.1700
Data Index: 6790473 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8165. Min Act: -0.1700
Data Index: 5088226 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8165. Min Act: -0.1700
Data Index: 8009844 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9416. Min Range: -3.9416
Max Act: 3.8165. Min Act: -0.1700
Data Index: 8226976 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19