Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1064. Min Range: -7.1064
Max Act: 7.1064. Min Act: -0.1700
Data Index: 2300203 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.7001. Min Act: -0.1700
Data Index: 8510548 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.6376. Min Act: -0.1700
Data Index: 4694217 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.5439. Min Act: -0.1700
Data Index: 7537489 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.5126. Min Act: -0.1700
Data Index: 7799550 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.5126. Min Act: -0.1700
Data Index: 6518481 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.4814. Min Act: -0.1700
Data Index: 6321187 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.4501. Min Act: -0.1700
Data Index: 8027613 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.3564. Min Act: -0.1700
Data Index: 3867483 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.3564. Min Act: -0.1700
Data Index: 3284657 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.3564. Min Act: -0.1700
Data Index: 773322 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.3876. Min Act: -0.1700
Data Index: 4157178 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.3564. Min Act: -0.1700
Data Index: 8418438 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.3564. Min Act: -0.1700
Data Index: 6256349 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.3251. Min Act: -0.1700
Data Index: 7096231 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.2939. Min Act: -0.1700
Data Index: 4886469 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.2939. Min Act: -0.1700
Data Index: 1020477 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.2939. Min Act: -0.1700
Data Index: 3583493 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.2626. Min Act: -0.1700
Data Index: 656753 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1064. Min Range: -7.1064
Max Act: 6.2939. Min Act: -0.1700
Data Index: 1381147 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19