Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 63 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.2441. Min Act: -0.1700
Data Index: 8437684 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.2753. Min Act: -0.1700
Data Index: 3602980 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.2128. Min Act: -0.1700
Data Index: 684185 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.2441. Min Act: -0.1700
Data Index: 8235440 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.2128. Min Act: -0.1700
Data Index: 8315700 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.1816. Min Act: -0.1700
Data Index: 4924660 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.1503. Min Act: -0.1700
Data Index: 5097682 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.1503. Min Act: -0.1700
Data Index: 2760732 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.1191. Min Act: -0.1700
Data Index: 5346319 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0878. Min Act: -0.1700
Data Index: 6262775 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0878. Min Act: -0.1700
Data Index: 2266243 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 7128204 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 1502779 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 4402928 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 8211776 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 2729073 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 2091387 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0566. Min Act: -0.1700
Data Index: 8756072 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0253. Min Act: -0.1700
Data Index: 6058041 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2753. Min Range: -5.2753
Max Act: 5.0253. Min Act: -0.1700
Data Index: 3423624 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19