Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3888 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2335. Min Range: -3.2335
Max Act: 3.2335. Min Act: -0.1700
Data Index: 616680 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2335. Min Range: -3.2335
Max Act: 3.0919. Min Act: -0.1700
Data Index: 1251915 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2335. Min Range: -3.2335
Max Act: 3.0446. Min Act: -0.1700
Data Index: 4157690 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9656. Min Act: -0.1700
Data Index: 3096162 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9814. Min Act: -0.1700
Data Index: 6413460 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9656. Min Act: -0.1700
Data Index: 8696837 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9656. Min Act: -0.1700
Data Index: 4254163 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9339. Min Act: -0.1700
Data Index: 6831337 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9656. Min Act: -0.1700
Data Index: 7800361 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9181. Min Act: -0.1700
Data Index: 6943872 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9181. Min Act: -0.1700
Data Index: 5305268 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9022. Min Act: -0.1700
Data Index: 5379111 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9022. Min Act: -0.1700
Data Index: 1261914 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9022. Min Act: -0.1700
Data Index: 1076943 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9181. Min Act: -0.1700
Data Index: 2659704 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.8864. Min Act: -0.1700
Data Index: 6750137 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.9022. Min Act: -0.1700
Data Index: 5402365 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.8705. Min Act: -0.1700
Data Index: 1227656 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.8864. Min Act: -0.1700
Data Index: 3854241 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2335. Min Range: -3.2335
Max Act: 2.8705. Min Act: -0.1700
Data Index: 1570836 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19