Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.4862. Min Act: -0.1700
Data Index: 1002783 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.4550. Min Act: -0.1700
Data Index: 6868622 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.3925. Min Act: -0.1700
Data Index: 5482945 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.3925. Min Act: -0.1700
Data Index: 4358490 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.3612. Min Act: -0.1700
Data Index: 3034520 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2987. Min Act: -0.1700
Data Index: 1778084 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2987. Min Act: -0.1700
Data Index: 5378918 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.3612. Min Act: -0.1700
Data Index: 6212025 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.3612. Min Act: -0.1700
Data Index: 366793 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2675. Min Act: -0.1700
Data Index: 4231845 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2675. Min Act: -0.1700
Data Index: 974731 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2675. Min Act: -0.1700
Data Index: 5199588 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2362. Min Act: -0.1700
Data Index: 7254 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2675. Min Act: -0.1700
Data Index: 4975128 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2362. Min Act: -0.1700
Data Index: 2450246 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2675. Min Act: -0.1700
Data Index: 8682280 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2362. Min Act: -0.1700
Data Index: 6671168 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2362. Min Act: -0.1700
Data Index: 7105258 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2050. Min Act: -0.1700
Data Index: 4756647 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4862. Min Range: -4.4862
Max Act: 4.2362. Min Act: -0.1700
Data Index: 7159299 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19