Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.8464. Min Act: -0.1700
Data Index: 4650896 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.8152. Min Act: -0.1700
Data Index: 7153779 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.7527. Min Act: -0.1700
Data Index: 1528630 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.6902. Min Act: -0.1700
Data Index: 6217037 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.5652. Min Act: -0.1700
Data Index: 4686783 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.5339. Min Act: -0.1700
Data Index: 1255830 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.4402. Min Act: -0.1700
Data Index: 5958911 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.4089. Min Act: -0.1700
Data Index: 4764871 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.3777. Min Act: -0.1700
Data Index: 6798259 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.2839. Min Act: -0.1700
Data Index: 2288366 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.2839. Min Act: -0.1700
Data Index: 6754808 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.2214. Min Act: -0.1700
Data Index: 8762949 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.2527. Min Act: -0.1700
Data Index: 17208 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.1902. Min Act: -0.1700
Data Index: 391092 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.1902. Min Act: -0.1700
Data Index: 8364170 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.1902. Min Act: -0.1700
Data Index: 5717664 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.1589. Min Act: -0.1700
Data Index: 3730848 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.1589. Min Act: -0.1700
Data Index: 5196496 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.1589. Min Act: -0.1700
Data Index: 4599723 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8464. Min Range: -7.8464
Max Act: 7.1277. Min Act: -0.1700
Data Index: 2032216 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19