Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1961 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7033. Min Range: -6.7033
Max Act: 6.7033. Min Act: -0.1700
Data Index: 5687180 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7033. Min Range: -6.7033
Max Act: 6.3283. Min Act: -0.1700
Data Index: 1552368 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7033. Min Range: -6.7033
Max Act: 6.2346. Min Act: -0.1700
Data Index: 6461934 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7033. Min Range: -6.7033
Max Act: 6.0783. Min Act: -0.1700
Data Index: 4788973 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7033. Min Range: -6.7033
Max Act: 6.1096. Min Act: -0.1700
Data Index: 7487134 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7033. Min Range: -6.7033
Max Act: 6.0783. Min Act: -0.1700
Data Index: 2367497 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7033. Min Range: -6.7033
Max Act: 6.0158. Min Act: -0.1700
Data Index: 563681 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7033. Min Range: -6.7033
Max Act: 6.0158. Min Act: -0.1700
Data Index: 1118447 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.9846. Min Act: -0.1700
Data Index: 5850388 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.9533. Min Act: -0.1700
Data Index: 7646772 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.9533. Min Act: -0.1700
Data Index: 3186078 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.9533. Min Act: -0.1700
Data Index: 3676395 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.9221. Min Act: -0.1700
Data Index: 2866657 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6058701 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.9221. Min Act: -0.1700
Data Index: 8722316 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.8596. Min Act: -0.1700
Data Index: 1790848 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.8908. Min Act: -0.1700
Data Index: 8262611 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6309703 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.8908. Min Act: -0.1700
Data Index: 4117511 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7033. Min Range: -6.7033
Max Act: 5.8596. Min Act: -0.1700
Data Index: 7139193 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19