Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.5403. Min Act: -0.1700
Data Index: 7176502 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.5090. Min Act: -0.1700
Data Index: 1030482 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.4778. Min Act: -0.1700
Data Index: 2178493 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.4153. Min Act: -0.1700
Data Index: 3446270 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.3840. Min Act: -0.1700
Data Index: 552776 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.3215. Min Act: -0.1700
Data Index: 6283717 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.2903. Min Act: -0.1700
Data Index: 4758345 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.1965. Min Act: -0.1700
Data Index: 3118874 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.2278. Min Act: -0.1700
Data Index: 3235838 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.1340. Min Act: -0.1700
Data Index: 3737540 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.1340. Min Act: -0.1700
Data Index: 3488984 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.1028. Min Act: -0.1700
Data Index: 1920708 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.0403. Min Act: -0.1700
Data Index: 8652696 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.0715. Min Act: -0.1700
Data Index: 4048723 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.0715. Min Act: -0.1700
Data Index: 1715397 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.0403. Min Act: -0.1700
Data Index: 2255048 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.0403. Min Act: -0.1700
Data Index: 409356 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.0715. Min Act: -0.1700
Data Index: 5304933 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.0403. Min Act: -0.1700
Data Index: 896567 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5403. Min Range: -6.5403
Max Act: 6.0403. Min Act: -0.1700
Data Index: 949744 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19