Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.2153. Min Act: -0.1700
Data Index: 1585653 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.2310. Min Act: -0.1700
Data Index: 3268622 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1838. Min Act: -0.1700
Data Index: 5181757 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1838. Min Act: -0.1700
Data Index: 6721840 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1523. Min Act: -0.1700
Data Index: 6948312 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1681. Min Act: -0.1700
Data Index: 4567112 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1838. Min Act: -0.1700
Data Index: 7560953 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1366. Min Act: -0.1700
Data Index: 7348181 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1681. Min Act: -0.1700
Data Index: 3673757 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1681. Min Act: -0.1700
Data Index: 954297 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1681. Min Act: -0.1700
Data Index: 7169917 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1681. Min Act: -0.1700
Data Index: 4624485 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1208. Min Act: -0.1700
Data Index: 571155 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1838. Min Act: -0.1700
Data Index: 1411166 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1681. Min Act: -0.1700
Data Index: 4708154 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1681. Min Act: -0.1700
Data Index: 5533653 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1366. Min Act: -0.1700
Data Index: 2473432 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1366. Min Act: -0.1700
Data Index: 4856600 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1523. Min Act: -0.1700
Data Index: 4451189 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2310. Min Range: -3.2310
Max Act: 3.1366. Min Act: -0.1700
Data Index: 8347484 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19