Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7524. Min Range: -8.7524
Max Act: 8.7524. Min Act: -0.1700
Data Index: 7593335 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7524. Min Range: -8.7524
Max Act: 8.6899. Min Act: -0.1700
Data Index: 3442798 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7524. Min Range: -8.7524
Max Act: 8.5649. Min Act: -0.1700
Data Index: 5368309 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7524. Min Range: -8.7524
Max Act: 8.2524. Min Act: -0.1700
Data Index: 302613 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7524. Min Range: -8.7524
Max Act: 8.1899. Min Act: -0.1700
Data Index: 8528668 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7524. Min Range: -8.7524
Max Act: 8.1274. Min Act: -0.1700
Data Index: 7386767 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.9399. Min Act: -0.1700
Data Index: 2529396 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.8774. Min Act: -0.1700
Data Index: 2151651 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.8774. Min Act: -0.1700
Data Index: 2316179 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.8774. Min Act: -0.1700
Data Index: 7146740 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.8149. Min Act: -0.1700
Data Index: 4470731 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.7837. Min Act: -0.1700
Data Index: 1963104 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.7837. Min Act: -0.1700
Data Index: 350255 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.7212. Min Act: -0.1700
Data Index: 2521539 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.6899. Min Act: -0.1700
Data Index: 5838206 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.6274. Min Act: -0.1700
Data Index: 2471175 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.6274. Min Act: -0.1700
Data Index: 1175857 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.5962. Min Act: -0.1700
Data Index: 6098499 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.5337. Min Act: -0.1700
Data Index: 8184035 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7524. Min Range: -8.7524
Max Act: 7.5649. Min Act: -0.1700
Data Index: 3433847 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19