Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6107 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2446. Min Range: -7.2446
Max Act: 7.2446. Min Act: -0.1700
Data Index: 6891968 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.9009. Min Act: -0.1700
Data Index: 3269318 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.7446. Min Act: -0.1700
Data Index: 322869 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.7134. Min Act: -0.1700
Data Index: 1109879 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.7134. Min Act: -0.1700
Data Index: 1369947 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.6821. Min Act: -0.1700
Data Index: 8625802 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.6196. Min Act: -0.1700
Data Index: 8210011 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.6196. Min Act: -0.1700
Data Index: 1653359 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.5884. Min Act: -0.1700
Data Index: 3447051 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.5884. Min Act: -0.1700
Data Index: 404650 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.5571. Min Act: -0.1700
Data Index: 1843465 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.5259. Min Act: -0.1700
Data Index: 5611262 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.4946. Min Act: -0.1700
Data Index: 5447168 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.4946. Min Act: -0.1700
Data Index: 1951700 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.4946. Min Act: -0.1700
Data Index: 8330668 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.4946. Min Act: -0.1700
Data Index: 8225490 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.5259. Min Act: -0.1700
Data Index: 4992543 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.4634. Min Act: -0.1700
Data Index: 3265214 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.4634. Min Act: -0.1700
Data Index: 5697009 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2446. Min Range: -7.2446
Max Act: 6.4634. Min Act: -0.1700
Data Index: 7391973 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19