Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 267 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.5107. Min Act: -0.1700
Data Index: 8345775 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.2607. Min Act: -0.1700
Data Index: 1341925 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.2295. Min Act: -0.1700
Data Index: 7795544 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.1982. Min Act: -0.1700
Data Index: 4167607 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.1982. Min Act: -0.1700
Data Index: 5373743 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.1670. Min Act: -0.1700
Data Index: 7470340 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.1045. Min Act: -0.1700
Data Index: 5501606 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.1045. Min Act: -0.1700
Data Index: 1515695 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0420. Min Act: -0.1700
Data Index: 1069899 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0732. Min Act: -0.1700
Data Index: 4114196 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.1045. Min Act: -0.1700
Data Index: 542655 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0732. Min Act: -0.1700
Data Index: 5078273 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0732. Min Act: -0.1700
Data Index: 5001725 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0732. Min Act: -0.1700
Data Index: 6359811 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0732. Min Act: -0.1700
Data Index: 2515589 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0420. Min Act: -0.1700
Data Index: 5135627 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0420. Min Act: -0.1700
Data Index: 5818503 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0107. Min Act: -0.1700
Data Index: 3530231 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0107. Min Act: -0.1700
Data Index: 5852688 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5107. Min Range: -5.5107
Max Act: 5.0107. Min Act: -0.1700
Data Index: 6327890 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19