Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3287 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.3545. Min Act: -0.1700
Data Index: 4319295 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.3217. Min Act: -0.1700
Data Index: 896173 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2724. Min Act: -0.1700
Data Index: 4283030 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2558. Min Act: -0.1700
Data Index: 5963525 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2558. Min Act: -0.1700
Data Index: 5031476 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2393. Min Act: -0.1700
Data Index: 7920109 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2393. Min Act: -0.1700
Data Index: 2606119 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2393. Min Act: -0.1700
Data Index: 6397754 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2393. Min Act: -0.1700
Data Index: 7664146 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2228. Min Act: -0.1700
Data Index: 2926015 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2228. Min Act: -0.1700
Data Index: 977411 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2228. Min Act: -0.1700
Data Index: 6820543 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2393. Min Act: -0.1700
Data Index: 7439213 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2062. Min Act: -0.1700
Data Index: 1584470 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2062. Min Act: -0.1700
Data Index: 2865716 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.2062. Min Act: -0.1700
Data Index: 3792027 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.1896. Min Act: -0.1700
Data Index: 7643153 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.1896. Min Act: -0.1700
Data Index: 495221 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.1896. Min Act: -0.1700
Data Index: 4663290 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3545. Min Range: -2.3545
Max Act: 2.1896. Min Act: -0.1700
Data Index: 3688227 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19