Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2843 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.5084. Min Act: -0.1700
Data Index: 995860 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.5084. Min Act: -0.1700
Data Index: 7063897 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.3834. Min Act: -0.1700
Data Index: 1560100 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.3209. Min Act: -0.1700
Data Index: 6704259 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.2897. Min Act: -0.1700
Data Index: 7809322 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.2584. Min Act: -0.1700
Data Index: 1956475 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.2584. Min Act: -0.1700
Data Index: 4410468 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.1959. Min Act: -0.1700
Data Index: 4037953 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.2272. Min Act: -0.1700
Data Index: 625803 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.2272. Min Act: -0.1700
Data Index: 2933934 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.1959. Min Act: -0.1700
Data Index: 2754429 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.1959. Min Act: -0.1700
Data Index: 7453493 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.1959. Min Act: -0.1700
Data Index: 6068311 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.1647. Min Act: -0.1700
Data Index: 7537500 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.1647. Min Act: -0.1700
Data Index: 2124489 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.1647. Min Act: -0.1700
Data Index: 5263479 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.0709. Min Act: -0.1700
Data Index: 2493138 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.1022. Min Act: -0.1700
Data Index: 4793550 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.0709. Min Act: -0.1700
Data Index: 8768631 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5084. Min Range: -6.5084
Max Act: 6.0397. Min Act: -0.1700
Data Index: 2082930 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19