Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.4214. Min Act: -0.1700
Data Index: 4183707 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.4214. Min Act: -0.1700
Data Index: 2105660 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.3589. Min Act: -0.1700
Data Index: 8629732 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.3589. Min Act: -0.1700
Data Index: 3462229 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.3589. Min Act: -0.1700
Data Index: 8630675 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.3277. Min Act: -0.1700
Data Index: 154915 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.3277. Min Act: -0.1700
Data Index: 3270989 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2964. Min Act: -0.1700
Data Index: 7274562 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2652. Min Act: -0.1700
Data Index: 4718325 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2339. Min Act: -0.1700
Data Index: 8706560 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2652. Min Act: -0.1700
Data Index: 5406787 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2652. Min Act: -0.1700
Data Index: 599753 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2339. Min Act: -0.1700
Data Index: 48522 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2339. Min Act: -0.1700
Data Index: 5956323 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2027. Min Act: -0.1700
Data Index: 79777 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2027. Min Act: -0.1700
Data Index: 5068307 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2027. Min Act: -0.1700
Data Index: 1813853 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.2027. Min Act: -0.1700
Data Index: 1898326 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.1714. Min Act: -0.1700
Data Index: 574511 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4214. Min Range: -5.4214
Max Act: 5.1714. Min Act: -0.1700
Data Index: 2979683 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19