Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3199 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.8985. Min Act: -0.1700
Data Index: 5567536 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.8047. Min Act: -0.1700
Data Index: 3789381 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.7110. Min Act: -0.1700
Data Index: 2619639 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.6485. Min Act: -0.1700
Data Index: 7078830 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.6172. Min Act: -0.1700
Data Index: 6133553 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.6172. Min Act: -0.1700
Data Index: 3723261 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.5860. Min Act: -0.1700
Data Index: 6235691 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.5860. Min Act: -0.1700
Data Index: 4659520 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.5547. Min Act: -0.1700
Data Index: 6939891 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.5547. Min Act: -0.1700
Data Index: 7278528 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.5235. Min Act: -0.1700
Data Index: 8724192 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.5547. Min Act: -0.1700
Data Index: 3887883 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.5235. Min Act: -0.1700
Data Index: 8077158 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.4922. Min Act: -0.1700
Data Index: 3679988 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.4922. Min Act: -0.1700
Data Index: 250875 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.4922. Min Act: -0.1700
Data Index: 7014587 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.4922. Min Act: -0.1700
Data Index: 5360047 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.4922. Min Act: -0.1700
Data Index: 6114276 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.4922. Min Act: -0.1700
Data Index: 6816712 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8985. Min Range: -5.8985
Max Act: 5.4922. Min Act: -0.1700
Data Index: 5063213 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19