Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2834. Min Range: -5.2834
Max Act: 5.2834. Min Act: -0.1700
Data Index: 6592792 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2834. Min Range: -5.2834
Max Act: 5.0334. Min Act: -0.1700
Data Index: 4026651 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2834. Min Range: -5.2834
Max Act: 5.0021. Min Act: -0.1700
Data Index: 5647479 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2834. Min Range: -5.2834
Max Act: 5.0334. Min Act: -0.1700
Data Index: 4270498 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.9709. Min Act: -0.1700
Data Index: 3899402 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.9084. Min Act: -0.1700
Data Index: 915469 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8771. Min Act: -0.1700
Data Index: 4914680 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8771. Min Act: -0.1700
Data Index: 1294574 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8771. Min Act: -0.1700
Data Index: 2593325 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8459. Min Act: -0.1700
Data Index: 4864898 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8459. Min Act: -0.1700
Data Index: 7696121 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8459. Min Act: -0.1700
Data Index: 5233944 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8459. Min Act: -0.1700
Data Index: 5098436 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8146. Min Act: -0.1700
Data Index: 8784487 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.8146. Min Act: -0.1700
Data Index: 2593306 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.7521. Min Act: -0.1700
Data Index: 537181 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.7834. Min Act: -0.1700
Data Index: 6157308 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.7209. Min Act: -0.1700
Data Index: 7029653 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.7521. Min Act: -0.1700
Data Index: 617332 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2834. Min Range: -5.2834
Max Act: 4.7521. Min Act: -0.1700
Data Index: 5088629 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19