Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6278 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.9460. Min Act: -0.1700
Data Index: 5586377 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.8835. Min Act: -0.1700
Data Index: 6804086 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7897. Min Act: -0.1700
Data Index: 2468843 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.8210. Min Act: -0.1700
Data Index: 2063286 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7897. Min Act: -0.1700
Data Index: 8274754 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7897. Min Act: -0.1700
Data Index: 8426199 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7585. Min Act: -0.1700
Data Index: 4222506 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7585. Min Act: -0.1700
Data Index: 7223432 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7272. Min Act: -0.1700
Data Index: 1090753 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7272. Min Act: -0.1700
Data Index: 5044357 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7272. Min Act: -0.1700
Data Index: 2563262 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.7272. Min Act: -0.1700
Data Index: 5630219 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.6960. Min Act: -0.1700
Data Index: 5653000 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.6960. Min Act: -0.1700
Data Index: 6698937 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.6960. Min Act: -0.1700
Data Index: 973107 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.6647. Min Act: -0.1700
Data Index: 8293275 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.6335. Min Act: -0.1700
Data Index: 4927124 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.6647. Min Act: -0.1700
Data Index: 8282549 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.6022. Min Act: -0.1700
Data Index: 586368 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9460. Min Range: -6.9460
Max Act: 6.6335. Min Act: -0.1700
Data Index: 1289167 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19