Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1975 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.4972. Min Act: -0.1700
Data Index: 7487373 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.4347. Min Act: -0.1700
Data Index: 5448320 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.3722. Min Act: -0.1700
Data Index: 1013755 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.3409. Min Act: -0.1700
Data Index: 2024910 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.3409. Min Act: -0.1700
Data Index: 4930524 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.3097. Min Act: -0.1700
Data Index: 4379185 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2784. Min Act: -0.1700
Data Index: 194368 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2784. Min Act: -0.1700
Data Index: 7624133 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2784. Min Act: -0.1700
Data Index: 4366930 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2472. Min Act: -0.1700
Data Index: 5460175 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2472. Min Act: -0.1700
Data Index: 541805 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2472. Min Act: -0.1700
Data Index: 2608227 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2472. Min Act: -0.1700
Data Index: 3760662 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2472. Min Act: -0.1700
Data Index: 7789897 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2472. Min Act: -0.1700
Data Index: 1223351 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2159. Min Act: -0.1700
Data Index: 5264772 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2472. Min Act: -0.1700
Data Index: 6164125 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.1847. Min Act: -0.1700
Data Index: 7119978 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2159. Min Act: -0.1700
Data Index: 1375008 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4972. Min Range: -6.4972
Max Act: 6.2159. Min Act: -0.1700
Data Index: 4276921 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19