Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0237. Min Range: -5.0237
Max Act: 5.0237. Min Act: -0.1700
Data Index: 5023125 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.9925. Min Act: -0.1700
Data Index: 8537956 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.9612. Min Act: -0.1700
Data Index: 6850220 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.9612. Min Act: -0.1700
Data Index: 6278157 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.9300. Min Act: -0.1700
Data Index: 4000730 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8675. Min Act: -0.1700
Data Index: 5339116 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8675. Min Act: -0.1700
Data Index: 2879288 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8987. Min Act: -0.1700
Data Index: 2026494 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8675. Min Act: -0.1700
Data Index: 3706207 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8362. Min Act: -0.1700
Data Index: 3474836 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8362. Min Act: -0.1700
Data Index: 1350979 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8050. Min Act: -0.1700
Data Index: 266221 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8050. Min Act: -0.1700
Data Index: 2966525 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8050. Min Act: -0.1700
Data Index: 3701604 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8050. Min Act: -0.1700
Data Index: 2387981 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8050. Min Act: -0.1700
Data Index: 8476846 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.7737. Min Act: -0.1700
Data Index: 5016850 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.7737. Min Act: -0.1700
Data Index: 8798007 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.7737. Min Act: -0.1700
Data Index: 4908678 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0237. Min Range: -5.0237
Max Act: 4.8050. Min Act: -0.1700
Data Index: 5529082 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19