Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.3249. Min Act: -0.1700
Data Index: 5318595 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.3561. Min Act: -0.1700
Data Index: 2721651 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.2311. Min Act: -0.1700
Data Index: 6192721 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.2311. Min Act: -0.1700
Data Index: 129060 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1686. Min Act: -0.1700
Data Index: 1238344 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1686. Min Act: -0.1700
Data Index: 4463372 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1374. Min Act: -0.1700
Data Index: 5065623 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1374. Min Act: -0.1700
Data Index: 5249988 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1374. Min Act: -0.1700
Data Index: 6639040 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1061. Min Act: -0.1700
Data Index: 8520551 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1061. Min Act: -0.1700
Data Index: 2789067 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1374. Min Act: -0.1700
Data Index: 8488588 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.0749. Min Act: -0.1700
Data Index: 2118130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.0749. Min Act: -0.1700
Data Index: 4956774 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.1061. Min Act: -0.1700
Data Index: 4985237 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.0749. Min Act: -0.1700
Data Index: 1290768 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.0749. Min Act: -0.1700
Data Index: 7072414 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.0436. Min Act: -0.1700
Data Index: 1857011 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.0436. Min Act: -0.1700
Data Index: 1485217 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3561. Min Range: -6.3561
Max Act: 6.0436. Min Act: -0.1700
Data Index: 6020474 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19