Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 481 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.5865. Min Act: -0.1700
Data Index: 4583552 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.4615. Min Act: -0.1700
Data Index: 890131 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.3678. Min Act: -0.1700
Data Index: 992628 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.2740. Min Act: -0.1700
Data Index: 1815134 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.1490. Min Act: -0.1700
Data Index: 3579390 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.1490. Min Act: -0.1700
Data Index: 3369139 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.1178. Min Act: -0.1700
Data Index: 2315668 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.1178. Min Act: -0.1700
Data Index: 5764308 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5865. Min Range: -6.5865
Max Act: 6.0553. Min Act: -0.1700
Data Index: 5048265 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.9303. Min Act: -0.1700
Data Index: 3315270 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.8990. Min Act: -0.1700
Data Index: 8335579 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.8365. Min Act: -0.1700
Data Index: 4062431 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.8678. Min Act: -0.1700
Data Index: 1316616 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.8365. Min Act: -0.1700
Data Index: 1902706 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.8365. Min Act: -0.1700
Data Index: 1022838 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.7740. Min Act: -0.1700
Data Index: 5424848 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.8053. Min Act: -0.1700
Data Index: 211778 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.8365. Min Act: -0.1700
Data Index: 7385476 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.8053. Min Act: -0.1700
Data Index: 4685528 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5865. Min Range: -6.5865
Max Act: 5.7740. Min Act: -0.1700
Data Index: 1335003 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19