Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.9262. Min Act: -0.1700
Data Index: 3839884 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.8950. Min Act: -0.1700
Data Index: 8619614 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.8012. Min Act: -0.1700
Data Index: 5099576 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.8637. Min Act: -0.1700
Data Index: 8355819 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.7075. Min Act: -0.1700
Data Index: 3479610 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.6762. Min Act: -0.1700
Data Index: 4333623 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.6762. Min Act: -0.1700
Data Index: 3910395 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.6450. Min Act: -0.1700
Data Index: 6660126 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.6137. Min Act: -0.1700
Data Index: 5394061 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.5825. Min Act: -0.1700
Data Index: 7125687 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.5825. Min Act: -0.1700
Data Index: 8002821 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.5825. Min Act: -0.1700
Data Index: 5265705 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.5512. Min Act: -0.1700
Data Index: 1293257 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.4887. Min Act: -0.1700
Data Index: 1459229 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.4887. Min Act: -0.1700
Data Index: 1864769 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.4887. Min Act: -0.1700
Data Index: 3471802 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.4575. Min Act: -0.1700
Data Index: 2039142 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.4575. Min Act: -0.1700
Data Index: 4822708 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.4262. Min Act: -0.1700
Data Index: 3505842 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9262. Min Range: -6.9262
Max Act: 6.4262. Min Act: -0.1700
Data Index: 1450993 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19