Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5214 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.4306. Min Act: -0.1700
Data Index: 7267437 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.3681. Min Act: -0.1700
Data Index: 5424341 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.2743. Min Act: -0.1700
Data Index: 979298 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.2431. Min Act: -0.1700
Data Index: 4861533 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.1806. Min Act: -0.1700
Data Index: 441355 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.1181. Min Act: -0.1700
Data Index: 1181425 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.1181. Min Act: -0.1700
Data Index: 8347298 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.0868. Min Act: -0.1700
Data Index: 2672396 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4306. Min Range: -6.4306
Max Act: 6.0243. Min Act: -0.1700
Data Index: 6859395 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.9618. Min Act: -0.1700
Data Index: 8620133 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.9618. Min Act: -0.1700
Data Index: 3849626 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8681. Min Act: -0.1700
Data Index: 919088 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8368. Min Act: -0.1700
Data Index: 6201763 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8368. Min Act: -0.1700
Data Index: 1479856 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8368. Min Act: -0.1700
Data Index: 6872519 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8368. Min Act: -0.1700
Data Index: 1876439 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8056. Min Act: -0.1700
Data Index: 7337502 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8056. Min Act: -0.1700
Data Index: 220061 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8056. Min Act: -0.1700
Data Index: 4550638 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4306. Min Range: -6.4306
Max Act: 5.8368. Min Act: -0.1700
Data Index: 2406617 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19