Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4198 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.9892. Min Act: -0.1700
Data Index: 7044477 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.8017. Min Act: -0.1700
Data Index: 3461482 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.7079. Min Act: -0.1700
Data Index: 1032917 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.6142. Min Act: -0.1700
Data Index: 5667028 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.5829. Min Act: -0.1700
Data Index: 6033490 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.5204. Min Act: -0.1700
Data Index: 6649920 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.5204. Min Act: -0.1700
Data Index: 7142321 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.5204. Min Act: -0.1700
Data Index: 4194376 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.4267. Min Act: -0.1700
Data Index: 7916290 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.4579. Min Act: -0.1700
Data Index: 74663 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.4579. Min Act: -0.1700
Data Index: 599470 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.4267. Min Act: -0.1700
Data Index: 7161611 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.4579. Min Act: -0.1700
Data Index: 6803487 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.3954. Min Act: -0.1700
Data Index: 7800708 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.3954. Min Act: -0.1700
Data Index: 509014 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.3954. Min Act: -0.1700
Data Index: 7276944 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.3642. Min Act: -0.1700
Data Index: 2408406 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.3642. Min Act: -0.1700
Data Index: 1206756 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.3642. Min Act: -0.1700
Data Index: 6684839 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9892. Min Range: -6.9892
Max Act: 6.3329. Min Act: -0.1700
Data Index: 8417568 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19