Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 448 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4345. Min Range: -6.4345
Max Act: 6.4345. Min Act: -0.1700
Data Index: 948811 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4345. Min Range: -6.4345
Max Act: 6.4032. Min Act: -0.1700
Data Index: 3825330 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4345. Min Range: -6.4345
Max Act: 6.3720. Min Act: -0.1700
Data Index: 3006012 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4345. Min Range: -6.4345
Max Act: 6.2782. Min Act: -0.1700
Data Index: 8495244 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4345. Min Range: -6.4345
Max Act: 6.0595. Min Act: -0.1700
Data Index: 7368420 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9970. Min Act: -0.1700
Data Index: 6081341 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9970. Min Act: -0.1700
Data Index: 4792426 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9970. Min Act: -0.1700
Data Index: 1555110 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9345. Min Act: -0.1700
Data Index: 7758357 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9345. Min Act: -0.1700
Data Index: 3654706 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9657. Min Act: -0.1700
Data Index: 6388347 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9032. Min Act: -0.1700
Data Index: 738318 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9657. Min Act: -0.1700
Data Index: 7714733 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9657. Min Act: -0.1700
Data Index: 7918701 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9032. Min Act: -0.1700
Data Index: 1020365 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9032. Min Act: -0.1700
Data Index: 8678226 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.9345. Min Act: -0.1700
Data Index: 5196377 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.8720. Min Act: -0.1700
Data Index: 824550 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.8720. Min Act: -0.1700
Data Index: 78272 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4345. Min Range: -6.4345
Max Act: 5.8720. Min Act: -0.1700
Data Index: 7963671 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19