Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3599 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.6310. Min Act: -0.1700
Data Index: 7166210 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.5997. Min Act: -0.1700
Data Index: 6290369 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.4747. Min Act: -0.1700
Data Index: 525599 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.4435. Min Act: -0.1700
Data Index: 737183 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.4122. Min Act: -0.1700
Data Index: 6896657 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.3810. Min Act: -0.1700
Data Index: 7829700 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.3185. Min Act: -0.1700
Data Index: 4353387 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.2560. Min Act: -0.1700
Data Index: 2685110 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.2247. Min Act: -0.1700
Data Index: 3726787 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.2560. Min Act: -0.1700
Data Index: 6538010 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.2560. Min Act: -0.1700
Data Index: 1642524 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.2560. Min Act: -0.1700
Data Index: 4153664 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.1935. Min Act: -0.1700
Data Index: 2905025 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.1935. Min Act: -0.1700
Data Index: 1025429 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.1935. Min Act: -0.1700
Data Index: 3857250 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.1935. Min Act: -0.1700
Data Index: 4695976 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.1935. Min Act: -0.1700
Data Index: 1643308 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.1622. Min Act: -0.1700
Data Index: 1776736 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.1622. Min Act: -0.1700
Data Index: 2331528 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6310. Min Range: -5.6310
Max Act: 5.1622. Min Act: -0.1700
Data Index: 2517728 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19