Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2404 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.9375. Min Act: -0.1700
Data Index: 2261809 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.8750. Min Act: -0.1700
Data Index: 797035 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.6875. Min Act: -0.1700
Data Index: 1380955 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.8125. Min Act: -0.1700
Data Index: 1613329 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.6250. Min Act: -0.1700
Data Index: 3381751 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.6875. Min Act: -0.1700
Data Index: 6733455 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.4375. Min Act: -0.1700
Data Index: 1894288 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.5000. Min Act: -0.1700
Data Index: 539134 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.4375. Min Act: -0.1700
Data Index: 8479247 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.3750. Min Act: -0.1700
Data Index: 5111849 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.4375. Min Act: -0.1700
Data Index: 6993245 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.3750. Min Act: -0.1700
Data Index: 1577680 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.3125. Min Act: -0.1700
Data Index: 4594765 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.3125. Min Act: -0.1700
Data Index: 3527023 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.3125. Min Act: -0.1700
Data Index: 5597295 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.2500. Min Act: -0.1700
Data Index: 3895643 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.2500. Min Act: -0.1700
Data Index: 7217659 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.3125. Min Act: -0.1700
Data Index: 6808213 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.2500. Min Act: -0.1700
Data Index: 3069779 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9375. Min Range: -9.9375
Max Act: 9.2500. Min Act: -0.1700
Data Index: 3171641 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19