Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 945 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3917. Min Range: -5.3917
Max Act: 5.3917. Min Act: -0.1700
Data Index: 6775633 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3917. Min Range: -5.3917
Max Act: 5.2667. Min Act: -0.1700
Data Index: 3382078 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3917. Min Range: -5.3917
Max Act: 5.2355. Min Act: -0.1700
Data Index: 5857530 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3917. Min Range: -5.3917
Max Act: 5.1417. Min Act: -0.1700
Data Index: 2155517 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3917. Min Range: -5.3917
Max Act: 5.1105. Min Act: -0.1700
Data Index: 8329696 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3917. Min Range: -5.3917
Max Act: 5.0792. Min Act: -0.1700
Data Index: 8400563 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3917. Min Range: -5.3917
Max Act: 5.0792. Min Act: -0.1700
Data Index: 669329 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.9542. Min Act: -0.1700
Data Index: 3656496 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.9230. Min Act: -0.1700
Data Index: 3881649 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.9230. Min Act: -0.1700
Data Index: 1381284 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.8605. Min Act: -0.1700
Data Index: 3965030 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.8917. Min Act: -0.1700
Data Index: 6518678 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.8917. Min Act: -0.1700
Data Index: 4304979 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.8917. Min Act: -0.1700
Data Index: 8524624 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.9230. Min Act: -0.1700
Data Index: 6205937 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.9230. Min Act: -0.1700
Data Index: 3008152 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.8917. Min Act: -0.1700
Data Index: 6799890 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.8917. Min Act: -0.1700
Data Index: 1410466 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.9230. Min Act: -0.1700
Data Index: 2155513 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3917. Min Range: -5.3917
Max Act: 4.8605. Min Act: -0.1700
Data Index: 6495672 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19