Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1111 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.6846. Min Act: -0.1700
Data Index: 2196051 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.6221. Min Act: -0.1700
Data Index: 4900063 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.5283. Min Act: -0.1700
Data Index: 979319 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.5283. Min Act: -0.1700
Data Index: 7871953 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4971. Min Act: -0.1700
Data Index: 6438234 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4971. Min Act: -0.1700
Data Index: 6204995 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4971. Min Act: -0.1700
Data Index: 625051 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4658. Min Act: -0.1700
Data Index: 4869798 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4658. Min Act: -0.1700
Data Index: 3976082 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4658. Min Act: -0.1700
Data Index: 3365433 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4971. Min Act: -0.1700
Data Index: 4558555 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4658. Min Act: -0.1700
Data Index: 7443480 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4658. Min Act: -0.1700
Data Index: 5554739 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4658. Min Act: -0.1700
Data Index: 1178056 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4658. Min Act: -0.1700
Data Index: 4470419 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4658. Min Act: -0.1700
Data Index: 2959919 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4346. Min Act: -0.1700
Data Index: 562839 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4346. Min Act: -0.1697
Data Index: 3929875 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4346. Min Act: -0.1700
Data Index: 5680574 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6846. Min Range: -5.6846
Max Act: 5.4346. Min Act: -0.1700
Data Index: 2473182 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19