Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0336. Min Range: -2.0336
Max Act: 2.0336. Min Act: -0.1699
Data Index: 1892287 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.9321. Min Act: -0.1696
Data Index: 6172770 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.9321. Min Act: -0.1700
Data Index: 1310117 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.9151. Min Act: -0.1694
Data Index: 3261186 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8809. Min Act: -0.1684
Data Index: 4420264 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8809. Min Act: -0.1700
Data Index: 6908624 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8809. Min Act: -0.1700
Data Index: 325280 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8296. Min Act: -0.1697
Data Index: 2248098 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8467. Min Act: -0.1700
Data Index: 190049 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8296. Min Act: -0.1652
Data Index: 2084521 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8124. Min Act: -0.1700
Data Index: 3020490 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8467. Min Act: -0.1695
Data Index: 2343755 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8124. Min Act: -0.1700
Data Index: 8265130 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8124. Min Act: -0.1693
Data Index: 5915632 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8124. Min Act: -0.1694
Data Index: 7635848 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8124. Min Act: -0.1700
Data Index: 7391092 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8124. Min Act: -0.1699
Data Index: 5417094 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.7952. Min Act: -0.1698
Data Index: 5813576 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.8124. Min Act: -0.1700
Data Index: 2814084 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0336. Min Range: -2.0336
Max Act: 1.7780. Min Act: -0.1689
Data Index: 7792317 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19