Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1969 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.5318. Min Act: -0.1700
Data Index: 2354934 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.4381. Min Act: -0.1700
Data Index: 6496930 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.4068. Min Act: -0.1700
Data Index: 6915440 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.2818. Min Act: -0.1700
Data Index: 162393 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.3131. Min Act: -0.1700
Data Index: 5385322 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.2193. Min Act: -0.1700
Data Index: 5742009 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.2193. Min Act: -0.1700
Data Index: 8641526 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.2506. Min Act: -0.1700
Data Index: 8591496 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1881. Min Act: -0.1700
Data Index: 6575487 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1568. Min Act: -0.1700
Data Index: 2814435 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1568. Min Act: -0.1700
Data Index: 5133510 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1256. Min Act: -0.1700
Data Index: 7622296 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1568. Min Act: -0.1700
Data Index: 8003702 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1568. Min Act: -0.1700
Data Index: 2297572 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.0943. Min Act: -0.1700
Data Index: 1202174 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1256. Min Act: -0.1700
Data Index: 619016 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1256. Min Act: -0.1700
Data Index: 4543491 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1256. Min Act: -0.1700
Data Index: 1631164 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1568. Min Act: -0.1700
Data Index: 2304060 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5318. Min Range: -6.5318
Max Act: 6.1568. Min Act: -0.1700
Data Index: 3052144 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19