Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 518 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.9727. Min Act: -0.1700
Data Index: 2304057 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8789. Min Act: -0.1700
Data Index: 217541 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8789. Min Act: -0.1700
Data Index: 5260675 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8789. Min Act: -0.1700
Data Index: 2209418 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8789. Min Act: -0.1700
Data Index: 752974 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8789. Min Act: -0.1700
Data Index: 3085528 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8477. Min Act: -0.1700
Data Index: 140513 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8477. Min Act: -0.1700
Data Index: 6366894 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8477. Min Act: -0.1700
Data Index: 803991 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8477. Min Act: -0.1700
Data Index: 7558272 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8477. Min Act: -0.1700
Data Index: 8330639 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 6394047 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 1024048 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 1565341 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 3669045 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 4310315 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 7148307 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 1888223 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 6315985 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9727. Min Range: -3.9727
Max Act: 3.8164. Min Act: -0.1700
Data Index: 5829614 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19