Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 870 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2198817 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.3571. Min Act: -0.1700
Data Index: 5695611 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.3259. Min Act: -0.1700
Data Index: 5695609 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.2321. Min Act: -0.1700
Data Index: 5695610 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.2321. Min Act: -0.1700
Data Index: 818277 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.2009. Min Act: -0.1700
Data Index: 694890 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.1696. Min Act: -0.1700
Data Index: 818278 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.1696. Min Act: -0.1700
Data Index: 329862 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.1696. Min Act: -0.1700
Data Index: 414477 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.1071. Min Act: -0.1700
Data Index: 5674798 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.1384. Min Act: -0.1700
Data Index: 3281136 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.0759. Min Act: -0.1700
Data Index: 6104617 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.0446. Min Act: -0.1700
Data Index: 7520160 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3884. Min Range: -5.3884
Max Act: 5.0134. Min Act: -0.1700
Data Index: 5720200 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3884. Min Range: -5.3884
Max Act: 4.9821. Min Act: -0.1700
Data Index: 8286696 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3884. Min Range: -5.3884
Max Act: 4.9509. Min Act: -0.1700
Data Index: 7520154 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3884. Min Range: -5.3884
Max Act: 4.9509. Min Act: -0.1700
Data Index: 6165741 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3884. Min Range: -5.3884
Max Act: 4.9509. Min Act: -0.1700
Data Index: 7520144 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3884. Min Range: -5.3884
Max Act: 4.9509. Min Act: -0.1700
Data Index: 818276 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3884. Min Range: -5.3884
Max Act: 4.9509. Min Act: -0.1700
Data Index: 8529411 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19