Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1792 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.3407. Min Act: -0.1700
Data Index: 1518092 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.2779. Min Act: -0.1700
Data Index: 1512598 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.1993. Min Act: -0.1700
Data Index: 1527894 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.1679. Min Act: -0.1700
Data Index: 2590804 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.1364. Min Act: -0.1700
Data Index: 7973466 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.1049. Min Act: -0.1700
Data Index: 4126382 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.1206. Min Act: -0.1700
Data Index: 4010234 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0733. Min Act: -0.1700
Data Index: 1105577 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0733. Min Act: -0.1700
Data Index: 6580126 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0576. Min Act: -0.1700
Data Index: 6202684 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0418. Min Act: -0.1700
Data Index: 266859 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0418. Min Act: -0.1700
Data Index: 169040 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0260. Min Act: -0.1700
Data Index: 1942329 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0260. Min Act: -0.1700
Data Index: 6018166 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0260. Min Act: -0.1700
Data Index: 5915088 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3407. Min Range: -3.3407
Max Act: 3.0102. Min Act: -0.1700
Data Index: 2450700 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3407. Min Range: -3.3407
Max Act: 2.9944. Min Act: -0.1700
Data Index: 634684 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3407. Min Range: -3.3407
Max Act: 2.9944. Min Act: -0.1700
Data Index: 3863977 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3407. Min Range: -3.3407
Max Act: 2.9944. Min Act: -0.1700
Data Index: 979895 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3407. Min Range: -3.3407
Max Act: 2.9944. Min Act: -0.1700
Data Index: 6219985 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19