Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.8343. Min Act: -0.1700
Data Index: 3978352 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.8343. Min Act: -0.1700
Data Index: 1397413 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.8030. Min Act: -0.1700
Data Index: 3861696 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.7405. Min Act: -0.1700
Data Index: 2887764 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.6780. Min Act: -0.1700
Data Index: 6089171 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.7093. Min Act: -0.1700
Data Index: 3085529 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.6155. Min Act: -0.1700
Data Index: 4011953 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.6468. Min Act: -0.1700
Data Index: 7836294 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.6155. Min Act: -0.1700
Data Index: 8399280 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5530. Min Act: -0.1700
Data Index: 4232024 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5843. Min Act: -0.1700
Data Index: 2660832 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5843. Min Act: -0.1700
Data Index: 6113677 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5530. Min Act: -0.1700
Data Index: 406286 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5218. Min Act: -0.1700
Data Index: 2151884 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5530. Min Act: -0.1700
Data Index: 2320222 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5218. Min Act: -0.1700
Data Index: 5353474 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5218. Min Act: -0.1700
Data Index: 1194104 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5218. Min Act: -0.1700
Data Index: 5883757 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.5218. Min Act: -0.1700
Data Index: 1907777 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8343. Min Range: -5.8343
Max Act: 5.4905. Min Act: -0.1700
Data Index: 4889767 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19