Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2417 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.5189. Min Act: -0.1700
Data Index: 8280209 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.1127. Min Act: -0.1700
Data Index: 423100 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.0814. Min Act: -0.1700
Data Index: 836678 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.0814. Min Act: -0.1700
Data Index: 4193856 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5189. Min Range: -5.5189
Max Act: 5.0189. Min Act: -0.1700
Data Index: 6963196 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.9564. Min Act: -0.1700
Data Index: 6896315 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.9564. Min Act: -0.1700
Data Index: 362222 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.9252. Min Act: -0.1700
Data Index: 7097498 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.9252. Min Act: -0.1700
Data Index: 3350038 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.9564. Min Act: -0.1700
Data Index: 1104255 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8939. Min Act: -0.1700
Data Index: 5479347 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8627. Min Act: -0.1700
Data Index: 1257410 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8939. Min Act: -0.1700
Data Index: 5206983 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8939. Min Act: -0.1700
Data Index: 8705746 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8314. Min Act: -0.1700
Data Index: 4809362 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8627. Min Act: -0.1700
Data Index: 1399336 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8002. Min Act: -0.1700
Data Index: 678986 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8627. Min Act: -0.1700
Data Index: 8278420 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8002. Min Act: -0.1700
Data Index: 2522391 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5189. Min Range: -5.5189
Max Act: 4.8314. Min Act: -0.1700
Data Index: 6042728 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19