Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1126 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7139. Min Range: -7.7139
Max Act: 7.7139. Min Act: -0.1700
Data Index: 8308630 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7139. Min Range: -7.7139
Max Act: 7.3389. Min Act: -0.1700
Data Index: 1150612 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7139. Min Range: -7.7139
Max Act: 7.3076. Min Act: -0.1700
Data Index: 6245256 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.9014. Min Act: -0.1700
Data Index: 4786674 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.8701. Min Act: -0.1700
Data Index: 5753905 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.8701. Min Act: -0.1700
Data Index: 7332512 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.8389. Min Act: -0.1700
Data Index: 532013 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.7764. Min Act: -0.1700
Data Index: 283610 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.7764. Min Act: -0.1700
Data Index: 2918043 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.7451. Min Act: -0.1700
Data Index: 7758695 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6826. Min Act: -0.1700
Data Index: 5036008 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.7139. Min Act: -0.1700
Data Index: 3256464 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6826. Min Act: -0.1700
Data Index: 8688312 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6826. Min Act: -0.1700
Data Index: 1673278 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6514. Min Act: -0.1700
Data Index: 6724683 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6514. Min Act: -0.1700
Data Index: 6831694 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6514. Min Act: -0.1700
Data Index: 7977349 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6514. Min Act: -0.1700
Data Index: 8684989 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6201. Min Act: -0.1700
Data Index: 4237699 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7139. Min Range: -7.7139
Max Act: 6.6201. Min Act: -0.1700
Data Index: 618494 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19