Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2398 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.3642. Min Act: -0.1694
Data Index: 1249190 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.1828. Min Act: -0.1683
Data Index: 2822874 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.1828. Min Act: -0.1700
Data Index: 1802581 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.1495. Min Act: -0.1700
Data Index: 8806306 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.1495. Min Act: -0.1700
Data Index: 124279 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.1495. Min Act: -0.1690
Data Index: 1921464 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.1495. Min Act: -0.1689
Data Index: 1678583 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0994. Min Act: -0.1632
Data Index: 6453902 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.1162. Min Act: -0.1698
Data Index: 486149 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0659. Min Act: -0.1700
Data Index: 8552536 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0994. Min Act: -0.1698
Data Index: 6459435 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0659. Min Act: -0.1681
Data Index: 1359754 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0827. Min Act: -0.1700
Data Index: 8570959 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0659. Min Act: -0.1691
Data Index: 3839407 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0659. Min Act: -0.1693
Data Index: 7514621 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0827. Min Act: -0.1632
Data Index: 2624888 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0659. Min Act: -0.1700
Data Index: 34913 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0659. Min Act: -0.1632
Data Index: 4462436 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3642. Min Range: -2.3642
Max Act: 2.0154. Min Act: -0.1700
Data Index: 6530491 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3642. Min Range: -2.3642
Max Act: 1.9985. Min Act: -0.1665
Data Index: 2073668 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19