Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.7656. Min Act: -0.1700
Data Index: 7162377 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.5781. Min Act: -0.1700
Data Index: 5705979 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.5156. Min Act: -0.1700
Data Index: 4626410 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.4531. Min Act: -0.1700
Data Index: 792649 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.4531. Min Act: -0.1700
Data Index: 2831535 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.3281. Min Act: -0.1700
Data Index: 7209549 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.3281. Min Act: -0.1700
Data Index: 6178214 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.2031. Min Act: -0.1700
Data Index: 2003167 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.2656. Min Act: -0.1700
Data Index: 4635608 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.2656. Min Act: -0.1700
Data Index: 5101487 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.2031. Min Act: -0.1700
Data Index: 6693668 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.2031. Min Act: -0.1700
Data Index: 2853664 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.2031. Min Act: -0.1700
Data Index: 7717183 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.2031. Min Act: -0.1700
Data Index: 4754710 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.2031. Min Act: -0.1700
Data Index: 711606 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.1406. Min Act: -0.1700
Data Index: 7670589 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.1406. Min Act: -0.1700
Data Index: 3671353 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.1406. Min Act: -0.1700
Data Index: 3810028 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.0781. Min Act: -0.1700
Data Index: 2196602 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7656. Min Range: -8.7656
Max Act: 8.0781. Min Act: -0.1700
Data Index: 5658368 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19