Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.1850. Min Act: -0.1700
Data Index: 756075 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.1225. Min Act: -0.1700
Data Index: 264115 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0912. Min Act: -0.1700
Data Index: 8553849 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0912. Min Act: -0.1700
Data Index: 8183081 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0912. Min Act: -0.1700
Data Index: 4472551 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0599. Min Act: -0.1700
Data Index: 3414746 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0912. Min Act: -0.1700
Data Index: 3511859 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0912. Min Act: -0.1700
Data Index: 125171 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0599. Min Act: -0.1700
Data Index: 2574358 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0287. Min Act: -0.1700
Data Index: 8150642 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0287. Min Act: -0.1700
Data Index: 6071457 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0287. Min Act: -0.1700
Data Index: 828637 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0287. Min Act: -0.1700
Data Index: 264114 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1850. Min Range: -4.1850
Max Act: 4.0599. Min Act: -0.1700
Data Index: 4030933 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1850. Min Range: -4.1850
Max Act: 3.9974. Min Act: -0.1700
Data Index: 5243290 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1850. Min Range: -4.1850
Max Act: 3.9974. Min Act: -0.1700
Data Index: 4524009 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1850. Min Range: -4.1850
Max Act: 3.9974. Min Act: -0.1700
Data Index: 2538157 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1850. Min Range: -4.1850
Max Act: 3.9974. Min Act: -0.1700
Data Index: 8150644 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1850. Min Range: -4.1850
Max Act: 3.9974. Min Act: -0.1700
Data Index: 3932968 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1850. Min Range: -4.1850
Max Act: 3.9974. Min Act: -0.1700
Data Index: 3975285 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19