Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1924 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.7608. Min Act: -0.1700
Data Index: 7668158 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.7608. Min Act: -0.1699
Data Index: 6183427 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.7296. Min Act: -0.1700
Data Index: 2678558 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.7921. Min Act: -0.1700
Data Index: 1397396 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.7608. Min Act: -0.1700
Data Index: 1481814 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.7608. Min Act: -0.1700
Data Index: 1864563 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6671. Min Act: -0.1700
Data Index: 4158540 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.7608. Min Act: -0.1700
Data Index: 393373 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6671. Min Act: -0.1700
Data Index: 2222046 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6983. Min Act: -0.1700
Data Index: 2066657 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6358. Min Act: -0.1700
Data Index: 5334298 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6671. Min Act: -0.1695
Data Index: 1486844 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6983. Min Act: -0.1700
Data Index: 4783382 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6358. Min Act: -0.1700
Data Index: 1946446 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6671. Min Act: -0.1700
Data Index: 3401431 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6358. Min Act: -0.1700
Data Index: 1669472 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6358. Min Act: -0.1700
Data Index: 3734754 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6358. Min Act: -0.1700
Data Index: 3836328 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6671. Min Act: -0.1700
Data Index: 4837653 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7921. Min Range: -4.7921
Max Act: 4.6358. Min Act: -0.1700
Data Index: 5437653 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19