Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0226. Min Range: -5.0226
Max Act: 5.0226. Min Act: -0.1700
Data Index: 2100015 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.4601. Min Act: -0.1700
Data Index: 4168492 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.4288. Min Act: -0.1700
Data Index: 6549697 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.4288. Min Act: -0.1700
Data Index: 8773284 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.3663. Min Act: -0.1700
Data Index: 8389780 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.3351. Min Act: -0.1700
Data Index: 3333183 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.3038. Min Act: -0.1700
Data Index: 8364394 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.2726. Min Act: -0.1700
Data Index: 4200370 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.2726. Min Act: -0.1700
Data Index: 1800279 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.2413. Min Act: -0.1700
Data Index: 5988376 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.2413. Min Act: -0.1700
Data Index: 7791515 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.2413. Min Act: -0.1700
Data Index: 6881474 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.2100. Min Act: -0.1700
Data Index: 8021870 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.2100. Min Act: -0.1700
Data Index: 4786564 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.1475. Min Act: -0.1700
Data Index: 5420436 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.2100. Min Act: -0.1700
Data Index: 6924436 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.1475. Min Act: -0.1700
Data Index: 5723669 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.1475. Min Act: -0.1700
Data Index: 2564569 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.1788. Min Act: -0.1700
Data Index: 244603 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0226. Min Range: -5.0226
Max Act: 4.1163. Min Act: -0.1700
Data Index: 30673 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19