Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.5510. Min Act: -0.1700
Data Index: 6389401 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.5510. Min Act: -0.1700
Data Index: 6338520 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4885. Min Act: -0.1700
Data Index: 7399791 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4885. Min Act: -0.1700
Data Index: 7827867 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4885. Min Act: -0.1700
Data Index: 616304 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4885. Min Act: -0.1700
Data Index: 3488930 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 5086232 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 4252262 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 2726532 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 7352841 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 1905371 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 5394528 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 2300760 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.4260. Min Act: -0.1700
Data Index: 4677126 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 736507 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 7300505 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 7084392 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 365651 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 4382977 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5510. Min Range: -7.5510
Max Act: 7.3635. Min Act: -0.1700
Data Index: 2108137 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19