Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0204. Min Range: -6.0204
Max Act: 6.0204. Min Act: -0.1700
Data Index: 7932557 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8641. Min Act: -0.1700
Data Index: 1381163 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8641. Min Act: -0.1700
Data Index: 543388 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8016. Min Act: -0.1700
Data Index: 2806781 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.8329. Min Act: -0.1700
Data Index: 1388079 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7704. Min Act: -0.1700
Data Index: 7297384 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7391. Min Act: -0.1700
Data Index: 1381161 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.7391. Min Act: -0.1700
Data Index: 4436095 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6141. Min Act: -0.1700
Data Index: 5326172 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6454. Min Act: -0.1700
Data Index: 3550262 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6454. Min Act: -0.1700
Data Index: 2562935 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6454. Min Act: -0.1700
Data Index: 793831 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6454. Min Act: -0.1700
Data Index: 5673609 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6141. Min Act: -0.1700
Data Index: 5212332 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6141. Min Act: -0.1700
Data Index: 5326173 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6141. Min Act: -0.1700
Data Index: 6765486 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6141. Min Act: -0.1700
Data Index: 6765491 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6141. Min Act: -0.1700
Data Index: 4884451 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.6141. Min Act: -0.1700
Data Index: 2019964 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0204. Min Range: -6.0204
Max Act: 5.5829. Min Act: -0.1700
Data Index: 2050489 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19