Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.2011. Min Act: -0.1700
Data Index: 1496346 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.1073. Min Act: -0.1700
Data Index: 8234830 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2011. Min Range: -5.2011
Max Act: 5.0136. Min Act: -0.1698
Data Index: 6521782 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.8573. Min Act: -0.1699
Data Index: 1804863 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.8573. Min Act: -0.1700
Data Index: 465173 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.7323. Min Act: -0.1668
Data Index: 1159405 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.7323. Min Act: -0.1700
Data Index: 8484639 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.7010. Min Act: -0.1700
Data Index: 954798 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.6385. Min Act: -0.1700
Data Index: 3884621 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.6698. Min Act: -0.1700
Data Index: 7971938 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.6385. Min Act: -0.1699
Data Index: 2264845 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.6698. Min Act: -0.1668
Data Index: 1341803 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.6073. Min Act: -0.1700
Data Index: 4489382 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.6073. Min Act: -0.1699
Data Index: 8477036 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.6073. Min Act: -0.1700
Data Index: 6202357 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.5760. Min Act: -0.1668
Data Index: 6571075 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.5760. Min Act: -0.1700
Data Index: 2461320 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.6073. Min Act: -0.1700
Data Index: 7326514 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.5760. Min Act: -0.1668
Data Index: 1465461 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2011. Min Range: -5.2011
Max Act: 4.5135. Min Act: -0.1668
Data Index: 1602135 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19