Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1662 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4585. Min Range: -5.4585
Max Act: 5.4585. Min Act: -0.1700
Data Index: 1705342 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4585. Min Range: -5.4585
Max Act: 5.3023. Min Act: -0.1700
Data Index: 988460 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4585. Min Range: -5.4585
Max Act: 5.2085. Min Act: -0.1700
Data Index: 6110663 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4585. Min Range: -5.4585
Max Act: 5.1460. Min Act: -0.1700
Data Index: 3665892 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4585. Min Range: -5.4585
Max Act: 5.0523. Min Act: -0.1700
Data Index: 1850403 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4585. Min Range: -5.4585
Max Act: 5.0210. Min Act: -0.1699
Data Index: 8405719 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9898. Min Act: -0.1700
Data Index: 4827767 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9898. Min Act: -0.1700
Data Index: 8625271 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4585. Min Range: -5.4585
Max Act: 5.0210. Min Act: -0.1700
Data Index: 1781289 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9898. Min Act: -0.1700
Data Index: 7824894 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9898. Min Act: -0.1700
Data Index: 7915252 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9898. Min Act: -0.1700
Data Index: 4914024 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9585. Min Act: -0.1699
Data Index: 6795699 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9898. Min Act: -0.1700
Data Index: 8718603 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9585. Min Act: -0.1700
Data Index: 1576834 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9273. Min Act: -0.1700
Data Index: 7574052 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9585. Min Act: -0.1700
Data Index: 6993550 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9585. Min Act: -0.1700
Data Index: 1336989 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9585. Min Act: -0.1700
Data Index: 5139067 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4585. Min Range: -5.4585
Max Act: 4.9585. Min Act: -0.1700
Data Index: 8689314 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19