Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 906 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.6441. Min Act: -0.1700
Data Index: 1222854 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.5815. Min Act: -0.1700
Data Index: 816048 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.5502. Min Act: -0.1700
Data Index: 6618120 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.5189. Min Act: -0.1700
Data Index: 1681041 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.4562. Min Act: -0.1700
Data Index: 2897738 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.4249. Min Act: -0.1700
Data Index: 193184 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.4249. Min Act: -0.1700
Data Index: 4838718 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3778. Min Act: -0.1700
Data Index: 2525626 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3935. Min Act: -0.1700
Data Index: 2268108 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3778. Min Act: -0.1700
Data Index: 2842126 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3621. Min Act: -0.1700
Data Index: 2593752 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3621. Min Act: -0.1700
Data Index: 6187927 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3778. Min Act: -0.1700
Data Index: 2563607 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3308. Min Act: -0.1700
Data Index: 3503405 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3464. Min Act: -0.1700
Data Index: 7011400 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3308. Min Act: -0.1700
Data Index: 4829839 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3308. Min Act: -0.1700
Data Index: 226765 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3308. Min Act: -0.1700
Data Index: 3731384 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.2994. Min Act: -0.1700
Data Index: 4152027 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6441. Min Range: -3.6441
Max Act: 3.3151. Min Act: -0.1700
Data Index: 3402695 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19