Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1096 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.9296. Min Act: -0.1700
Data Index: 5831656 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.8671. Min Act: -0.1700
Data Index: 5831664 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.8359. Min Act: -0.1700
Data Index: 1221944 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.8046. Min Act: -0.1700
Data Index: 1311732 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.7734. Min Act: -0.1700
Data Index: 89859 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.7109. Min Act: -0.1700
Data Index: 5726221 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.6171. Min Act: -0.1699
Data Index: 909426 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.5859. Min Act: -0.1700
Data Index: 5644812 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.5546. Min Act: -0.1700
Data Index: 3277009 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.5859. Min Act: -0.1700
Data Index: 2728650 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.5234. Min Act: -0.1700
Data Index: 4124264 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.5234. Min Act: -0.1700
Data Index: 5726220 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.4921. Min Act: -0.1700
Data Index: 5255129 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.5234. Min Act: -0.1700
Data Index: 1046096 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.4921. Min Act: -0.1700
Data Index: 2782661 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.4921. Min Act: -0.1700
Data Index: 2494375 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.4921. Min Act: -0.1700
Data Index: 1688558 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.4921. Min Act: -0.1699
Data Index: 573356 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.4921. Min Act: -0.1700
Data Index: 6281445 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9296. Min Range: -5.9296
Max Act: 5.5234. Min Act: -0.1700
Data Index: 3443087 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19