Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1042 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.6424. Min Act: -0.1700
Data Index: 1719236 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.2362. Min Act: -0.1700
Data Index: 1183521 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.1737. Min Act: -0.1700
Data Index: 8532786 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.1737. Min Act: -0.1700
Data Index: 4513440 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.1112. Min Act: -0.1700
Data Index: 7160955 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.0799. Min Act: -0.1700
Data Index: 929899 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.0174. Min Act: -0.1700
Data Index: 8532785 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.0487. Min Act: -0.1700
Data Index: 5878743 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.9862. Min Act: -0.1700
Data Index: 8532784 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6424. Min Range: -6.6424
Max Act: 6.0174. Min Act: -0.1700
Data Index: 5284336 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.9549. Min Act: -0.1700
Data Index: 5279962 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.9237. Min Act: -0.1700
Data Index: 299097 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.8924. Min Act: -0.1700
Data Index: 5920290 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.9237. Min Act: -0.1700
Data Index: 4983150 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.9237. Min Act: -0.1700
Data Index: 2935988 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.9237. Min Act: -0.1700
Data Index: 8321502 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.8924. Min Act: -0.1700
Data Index: 4004340 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.8612. Min Act: -0.1700
Data Index: 4051209 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.8924. Min Act: -0.1700
Data Index: 7147169 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6424. Min Range: -6.6424
Max Act: 5.8299. Min Act: -0.1700
Data Index: 6708889 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19