Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 963 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.9517. Min Act: -0.1700
Data Index: 3159216 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.9517. Min Act: -0.1700
Data Index: 1612991 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.9205. Min Act: -0.1700
Data Index: 811334 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.8580. Min Act: -0.1700
Data Index: 5745693 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.8267. Min Act: -0.1700
Data Index: 1493801 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.7955. Min Act: -0.1700
Data Index: 4326498 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.7330. Min Act: -0.1700
Data Index: 1790154 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.6705. Min Act: -0.1700
Data Index: 2523604 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.6080. Min Act: -0.1700
Data Index: 5436150 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.5767. Min Act: -0.1700
Data Index: 1186022 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.5455. Min Act: -0.1700
Data Index: 203509 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.5455. Min Act: -0.1700
Data Index: 7239567 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.5142. Min Act: -0.1700
Data Index: 8718576 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.5142. Min Act: -0.1700
Data Index: 7515696 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.5142. Min Act: -0.1700
Data Index: 4372632 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.4517. Min Act: -0.1700
Data Index: 3601715 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.4830. Min Act: -0.1700
Data Index: 3953292 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.4830. Min Act: -0.1700
Data Index: 7599310 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.4830. Min Act: -0.1700
Data Index: 541914 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9517. Min Range: -4.9517
Max Act: 4.4830. Min Act: -0.1700
Data Index: 6801670 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19