Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2127 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.5500. Min Act: -0.1700
Data Index: 8292088 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.4250. Min Act: -0.1700
Data Index: 100138 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.3625. Min Act: -0.1700
Data Index: 6061571 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.2375. Min Act: -0.1700
Data Index: 283031 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.1750. Min Act: -0.1700
Data Index: 5629383 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.1750. Min Act: -0.1700
Data Index: 4601215 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.1750. Min Act: -0.1700
Data Index: 2337394 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.1125. Min Act: -0.1700
Data Index: 3005803 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.1125. Min Act: -0.1700
Data Index: 2659506 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.1125. Min Act: -0.1700
Data Index: 7202911 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.1125. Min Act: -0.1700
Data Index: 1478380 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5500. Min Range: -8.5500
Max Act: 7.9875. Min Act: -0.1700
Data Index: 1512385 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.0500. Min Act: -0.1700
Data Index: 8161559 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5500. Min Range: -8.5500
Max Act: 7.9875. Min Act: -0.1700
Data Index: 7347406 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5500. Min Range: -8.5500
Max Act: 7.9875. Min Act: -0.1700
Data Index: 90944 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5500. Min Range: -8.5500
Max Act: 7.9875. Min Act: -0.1700
Data Index: 1438272 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5500. Min Range: -8.5500
Max Act: 7.9875. Min Act: -0.1700
Data Index: 7162085 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5500. Min Range: -8.5500
Max Act: 7.9875. Min Act: -0.1700
Data Index: 1422372 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5500. Min Range: -8.5500
Max Act: 8.0500. Min Act: -0.1700
Data Index: 7787894 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5500. Min Range: -8.5500
Max Act: 7.9875. Min Act: -0.1700
Data Index: 8095201 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19