Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2077 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.7349. Min Act: -0.1700
Data Index: 2383765 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.7349. Min Act: -0.1700
Data Index: 5061852 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6723. Min Act: -0.1700
Data Index: 7401127 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.7036. Min Act: -0.1700
Data Index: 6164403 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.7036. Min Act: -0.1700
Data Index: 717782 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6723. Min Act: -0.1700
Data Index: 5846722 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6723. Min Act: -0.1700
Data Index: 6969966 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6410. Min Act: -0.1700
Data Index: 866889 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6410. Min Act: -0.1700
Data Index: 26498 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6097. Min Act: -0.1700
Data Index: 2806300 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6410. Min Act: -0.1700
Data Index: 2505080 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6410. Min Act: -0.1700
Data Index: 2332733 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6097. Min Act: -0.1700
Data Index: 5585833 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6097. Min Act: -0.1700
Data Index: 8477681 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6097. Min Act: -0.1700
Data Index: 3846141 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.6097. Min Act: -0.1700
Data Index: 5685746 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.5784. Min Act: -0.1700
Data Index: 5459704 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.5784. Min Act: -0.1700
Data Index: 2013652 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.5784. Min Act: -0.1700
Data Index: 2354004 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7349. Min Range: -3.7349
Max Act: 3.5784. Min Act: -0.1700
Data Index: 4608385 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19