Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 452 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9744. Min Act: -0.1700
Data Index: 6227511 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9585. Min Act: -0.1700
Data Index: 342837 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9427. Min Act: -0.1700
Data Index: 7778241 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9427. Min Act: -0.1700
Data Index: 3833231 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9427. Min Act: -0.1700
Data Index: 5257651 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9427. Min Act: -0.1700
Data Index: 3689464 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 6174363 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 6968456 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 579969 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 556354 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 8245262 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 510858 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 4799864 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 6132458 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 1518571 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 4129587 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9269. Min Act: -0.1700
Data Index: 1492277 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9110. Min Act: -0.1700
Data Index: 2040243 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9110. Min Act: -0.1700
Data Index: 5307049 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9744. Min Range: -2.9744
Max Act: 2.9110. Min Act: -0.1700
Data Index: 6287193 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19