Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3847. Min Range: -10.3847
Max Act: 10.3847. Min Act: -0.1700
Data Index: 57135 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3847. Min Range: -10.3847
Max Act: 10.1972. Min Act: -0.1700
Data Index: 1486664 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3847. Min Range: -10.3847
Max Act: 10.0097. Min Act: -0.1700
Data Index: 3028352 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.8222. Min Act: -0.1700
Data Index: 1780148 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.8222. Min Act: -0.1700
Data Index: 4786533 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.6347. Min Act: -0.1700
Data Index: 6521854 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.5722. Min Act: -0.1700
Data Index: 1379028 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.5722. Min Act: -0.1700
Data Index: 3720046 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.5097. Min Act: -0.1700
Data Index: 4611289 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.4472. Min Act: -0.1700
Data Index: 6741676 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.4472. Min Act: -0.1700
Data Index: 5833248 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.3847. Min Act: -0.1700
Data Index: 8627740 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.3847. Min Act: -0.1700
Data Index: 1247839 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.3847. Min Act: -0.1700
Data Index: 6444253 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.3847. Min Act: -0.1700
Data Index: 7446030 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.3222. Min Act: -0.1700
Data Index: 7608929 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.3222. Min Act: -0.1700
Data Index: 1252518 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.3222. Min Act: -0.1700
Data Index: 2145957 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.3222. Min Act: -0.1700
Data Index: 3372224 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3847. Min Range: -10.3847
Max Act: 9.2597. Min Act: -0.1700
Data Index: 6708753 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19