Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4037. Min Range: -6.4037
Max Act: 6.4037. Min Act: -0.1700
Data Index: 7841132 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.9975. Min Act: -0.1700
Data Index: 5032405 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.8725. Min Act: -0.1700
Data Index: 1359535 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.8725. Min Act: -0.1700
Data Index: 1794648 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.8725. Min Act: -0.1700
Data Index: 399065 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.9037. Min Act: -0.1700
Data Index: 7162499 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.7475. Min Act: -0.1700
Data Index: 3879730 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.7162. Min Act: -0.1700
Data Index: 5505271 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.6850. Min Act: -0.1700
Data Index: 7026914 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.7162. Min Act: -0.1700
Data Index: 5736881 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.6225. Min Act: -0.1700
Data Index: 7061223 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5600. Min Act: -0.1700
Data Index: 3596109 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5912. Min Act: -0.1700
Data Index: 1669371 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5600. Min Act: -0.1700
Data Index: 3659814 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5600. Min Act: -0.1700
Data Index: 7506509 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5600. Min Act: -0.1700
Data Index: 8351343 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5600. Min Act: -0.1700
Data Index: 366470 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5287. Min Act: -0.1700
Data Index: 6442954 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5287. Min Act: -0.1700
Data Index: 673065 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4037. Min Range: -6.4037
Max Act: 5.5287. Min Act: -0.1700
Data Index: 4809862 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19