Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.9470. Min Act: -0.1700
Data Index: 1002341 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.8845. Min Act: -0.1700
Data Index: 3683801 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.7907. Min Act: -0.1700
Data Index: 4256463 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.6970. Min Act: -0.1700
Data Index: 7875923 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.6657. Min Act: -0.1700
Data Index: 5162349 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.6345. Min Act: -0.1700
Data Index: 154528 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.6345. Min Act: -0.1700
Data Index: 2434487 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.6032. Min Act: -0.1700
Data Index: 7850959 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.6032. Min Act: -0.1700
Data Index: 7002548 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.6032. Min Act: -0.1700
Data Index: 1283711 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.6032. Min Act: -0.1700
Data Index: 1412509 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.5720. Min Act: -0.1700
Data Index: 2095918 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.5407. Min Act: -0.1700
Data Index: 4963938 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.5720. Min Act: -0.1700
Data Index: 2065727 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.5407. Min Act: -0.1700
Data Index: 5496159 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.5095. Min Act: -0.1700
Data Index: 1725101 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.5095. Min Act: -0.1700
Data Index: 2351414 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.5095. Min Act: -0.1700
Data Index: 8676462 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.4782. Min Act: -0.1700
Data Index: 615074 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9470. Min Range: -6.9470
Max Act: 6.5095. Min Act: -0.1700
Data Index: 188962 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19