Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.5528. Min Act: -0.1700
Data Index: 1030436 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.4278. Min Act: -0.1700
Data Index: 7741211 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.3653. Min Act: -0.1700
Data Index: 2905815 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.3341. Min Act: -0.1700
Data Index: 2507004 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.2403. Min Act: -0.1700
Data Index: 3685074 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.2716. Min Act: -0.1700
Data Index: 7694108 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.2091. Min Act: -0.1700
Data Index: 5174677 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.2091. Min Act: -0.1700
Data Index: 7741210 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.1778. Min Act: -0.1700
Data Index: 6234271 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.2091. Min Act: -0.1700
Data Index: 4176723 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.1465. Min Act: -0.1700
Data Index: 7705973 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.1465. Min Act: -0.1700
Data Index: 5042334 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.1153. Min Act: -0.1700
Data Index: 5054368 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.1465. Min Act: -0.1700
Data Index: 8388635 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.0840. Min Act: -0.1700
Data Index: 7325563 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.1153. Min Act: -0.1700
Data Index: 1230742 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.0840. Min Act: -0.1700
Data Index: 7458714 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.0840. Min Act: -0.1700
Data Index: 5174664 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.0215. Min Act: -0.1700
Data Index: 5174688 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5528. Min Range: -4.5528
Max Act: 4.0215. Min Act: -0.1700
Data Index: 5811687 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19