Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2864 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2485. Min Range: -10.2485
Max Act: 10.2485. Min Act: -0.1700
Data Index: 5204487 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2485. Min Range: -10.2485
Max Act: 10.1860. Min Act: -0.1700
Data Index: 5204486 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2485. Min Range: -10.2485
Max Act: 10.1235. Min Act: -0.1700
Data Index: 5204488 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.9360. Min Act: -0.1700
Data Index: 6902008 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.8735. Min Act: -0.1700
Data Index: 7464644 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.6860. Min Act: -0.1700
Data Index: 5204489 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.5610. Min Act: -0.1700
Data Index: 2702568 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.5610. Min Act: -0.1700
Data Index: 6481306 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.4985. Min Act: -0.1700
Data Index: 1237609 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.3110. Min Act: -0.1700
Data Index: 5417580 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.3735. Min Act: -0.1700
Data Index: 5105578 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.3110. Min Act: -0.1700
Data Index: 2367664 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.2485. Min Act: -0.1700
Data Index: 3044601 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.3110. Min Act: -0.1700
Data Index: 4762062 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.2485. Min Act: -0.1700
Data Index: 4640231 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.1860. Min Act: -0.1700
Data Index: 6007842 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.1860. Min Act: -0.1700
Data Index: 14496 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2485. Min Range: -10.2485
Max Act: 9.0610. Min Act: -0.1700
Data Index: 3879874 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2485. Min Range: -10.2485
Max Act: 8.9985. Min Act: -0.1700
Data Index: 2716194 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2485. Min Range: -10.2485
Max Act: 8.9985. Min Act: -0.1700
Data Index: 8619594 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19