Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.5495. Min Act: -0.1700
Data Index: 5607030 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.5182. Min Act: -0.1700
Data Index: 4504418 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.3307. Min Act: -0.1700
Data Index: 2583178 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2995. Min Act: -0.1700
Data Index: 2906371 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2682. Min Act: -0.1700
Data Index: 2201247 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2682. Min Act: -0.1700
Data Index: 6474398 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2682. Min Act: -0.1700
Data Index: 5681945 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2682. Min Act: -0.1700
Data Index: 7346946 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2682. Min Act: -0.1700
Data Index: 950093 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2370. Min Act: -0.1700
Data Index: 3040447 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2370. Min Act: -0.1700
Data Index: 2906370 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2370. Min Act: -0.1700
Data Index: 4927498 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6126225 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2370. Min Act: -0.1700
Data Index: 1639023 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2370. Min Act: -0.1700
Data Index: 2324464 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2057. Min Act: -0.1700
Data Index: 1020677 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2057. Min Act: -0.1700
Data Index: 3642740 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2057. Min Act: -0.1700
Data Index: 3692230 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2057. Min Act: -0.1700
Data Index: 2661156 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5495. Min Range: -6.5495
Max Act: 6.2057. Min Act: -0.1700
Data Index: 5156570 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19