Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4690 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2806. Min Range: -7.2806
Max Act: 7.2806. Min Act: -0.1700
Data Index: 3559925 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.9994. Min Act: -0.1700
Data Index: 7221080 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.9369. Min Act: -0.1700
Data Index: 1551884 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.8431. Min Act: -0.1700
Data Index: 2250451 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.7181. Min Act: -0.1700
Data Index: 4625427 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.7494. Min Act: -0.1700
Data Index: 1767185 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.6869. Min Act: -0.1700
Data Index: 1778010 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.6869. Min Act: -0.1700
Data Index: 7110802 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.6556. Min Act: -0.1700
Data Index: 5828298 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.6244. Min Act: -0.1700
Data Index: 8109685 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.5619. Min Act: -0.1700
Data Index: 8416165 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.5619. Min Act: -0.1700
Data Index: 715457 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.5306. Min Act: -0.1700
Data Index: 8172489 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.5306. Min Act: -0.1700
Data Index: 8202432 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.5306. Min Act: -0.1700
Data Index: 2307851 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.4681. Min Act: -0.1700
Data Index: 6201673 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.4994. Min Act: -0.1700
Data Index: 1884559 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.4994. Min Act: -0.1700
Data Index: 7458663 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.4681. Min Act: -0.1700
Data Index: 3589449 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2806. Min Range: -7.2806
Max Act: 6.4369. Min Act: -0.1700
Data Index: 2769449 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19