Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3015 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.4110. Min Act: -0.1700
Data Index: 2618436 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.3485. Min Act: -0.1700
Data Index: 4766875 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.2860. Min Act: -0.1700
Data Index: 6350520 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.1610. Min Act: -0.1700
Data Index: 1269053 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.1610. Min Act: -0.1700
Data Index: 8432259 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.0985. Min Act: -0.1700
Data Index: 4595895 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.0672. Min Act: -0.1700
Data Index: 8031898 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.0672. Min Act: -0.1700
Data Index: 888169 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.0360. Min Act: -0.1700
Data Index: 4361959 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4110. Min Range: -7.4110
Max Act: 7.0047. Min Act: -0.1700
Data Index: 6063841 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.9735. Min Act: -0.1700
Data Index: 7465334 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.9422. Min Act: -0.1700
Data Index: 5815297 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.9110. Min Act: -0.1700
Data Index: 6378701 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.8797. Min Act: -0.1700
Data Index: 225627 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.8797. Min Act: -0.1700
Data Index: 4171337 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.8485. Min Act: -0.1700
Data Index: 4361954 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.8172. Min Act: -0.1700
Data Index: 660810 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.8172. Min Act: -0.1700
Data Index: 6239404 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.7860. Min Act: -0.1700
Data Index: 22386 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4110. Min Range: -7.4110
Max Act: 6.8172. Min Act: -0.1700
Data Index: 4451711 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19