Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.4013. Min Act: -0.1700
Data Index: 8244178 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.3388. Min Act: -0.1700
Data Index: 6208324 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2451. Min Act: -0.1700
Data Index: 2335150 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2451. Min Act: -0.1700
Data Index: 2569206 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2451. Min Act: -0.1700
Data Index: 7528272 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2451. Min Act: -0.1700
Data Index: 323344 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.2138. Min Act: -0.1700
Data Index: 8143383 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1826. Min Act: -0.1700
Data Index: 8212738 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1826. Min Act: -0.1700
Data Index: 4750193 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1513. Min Act: -0.1700
Data Index: 1898923 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1826. Min Act: -0.1700
Data Index: 2569210 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1513. Min Act: -0.1700
Data Index: 8143380 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1201. Min Act: -0.1700
Data Index: 881597 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.1513. Min Act: -0.1700
Data Index: 1639020 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.0888. Min Act: -0.1700
Data Index: 8081924 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.0888. Min Act: -0.1700
Data Index: 4830506 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.0576. Min Act: -0.1700
Data Index: 4640116 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.0263. Min Act: -0.1700
Data Index: 4775261 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4013. Min Range: -5.4013
Max Act: 5.0263. Min Act: -0.1700
Data Index: 6024078 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4013. Min Range: -5.4013
Max Act: 4.9951. Min Act: -0.1700
Data Index: 1886506 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19