Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.1589. Min Act: -0.1700
Data Index: 7450817 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.1276. Min Act: -0.1700
Data Index: 1540014 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.0964. Min Act: -0.1700
Data Index: 3507014 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.0651. Min Act: -0.1700
Data Index: 2014895 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.0339. Min Act: -0.1700
Data Index: 7253011 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.0026. Min Act: -0.1700
Data Index: 2027099 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.0026. Min Act: -0.1700
Data Index: 12185 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.0026. Min Act: -0.1700
Data Index: 3158424 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.0026. Min Act: -0.1700
Data Index: 3755151 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1589. Min Range: -6.1589
Max Act: 6.0026. Min Act: -0.1700
Data Index: 3001331 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.9401. Min Act: -0.1700
Data Index: 4754434 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.9089. Min Act: -0.1700
Data Index: 485936 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.8776. Min Act: -0.1700
Data Index: 3466873 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.8776. Min Act: -0.1700
Data Index: 4489480 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.8776. Min Act: -0.1700
Data Index: 6802446 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.8464. Min Act: -0.1700
Data Index: 7836340 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.8464. Min Act: -0.1700
Data Index: 5228159 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.8464. Min Act: -0.1700
Data Index: 2964347 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.8151. Min Act: -0.1700
Data Index: 3000331 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1589. Min Range: -6.1589
Max Act: 5.8151. Min Act: -0.1700
Data Index: 6591500 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19