Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0444. Min Range: -5.0444
Max Act: 5.0444. Min Act: -0.1700
Data Index: 6343087 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0444. Min Range: -5.0444
Max Act: 5.0444. Min Act: -0.1700
Data Index: 8021259 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0444. Min Range: -5.0444
Max Act: 5.0132. Min Act: -0.1700
Data Index: 6723735 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0444. Min Range: -5.0444
Max Act: 5.0132. Min Act: -0.1700
Data Index: 1433153 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.9819. Min Act: -0.1700
Data Index: 1725187 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.9194. Min Act: -0.1700
Data Index: 5929738 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.8882. Min Act: -0.1700
Data Index: 475001 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.8257. Min Act: -0.1700
Data Index: 6533586 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.7944. Min Act: -0.1700
Data Index: 3635023 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.8257. Min Act: -0.1700
Data Index: 1018919 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.7007. Min Act: -0.1700
Data Index: 2817062 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.7007. Min Act: -0.1700
Data Index: 641918 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.7007. Min Act: -0.1700
Data Index: 5424126 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.6694. Min Act: -0.1700
Data Index: 8819819 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.6382. Min Act: -0.1700
Data Index: 6253460 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.6382. Min Act: -0.1700
Data Index: 6447023 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.6382. Min Act: -0.1700
Data Index: 2511753 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.6382. Min Act: -0.1700
Data Index: 7739329 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.6382. Min Act: -0.1700
Data Index: 6253463 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0444. Min Range: -5.0444
Max Act: 4.6069. Min Act: -0.1700
Data Index: 5007420 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19