Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2322 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.6393. Min Act: -0.1676
Data Index: 317141 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.5141. Min Act: -0.1537
Data Index: 4093983 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4827. Min Act: -0.1700
Data Index: 796429 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4514. Min Act: -0.1699
Data Index: 771522 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4514. Min Act: -0.1619
Data Index: 1546812 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4201. Min Act: -0.1604
Data Index: 2411349 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4201. Min Act: -0.1648
Data Index: 7745972 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4201. Min Act: -0.1690
Data Index: 756005 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4201. Min Act: -0.1700
Data Index: 659215 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4201. Min Act: -0.1694
Data Index: 7976745 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.4201. Min Act: -0.1688
Data Index: 744544 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3887. Min Act: -0.1692
Data Index: 3842531 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3887. Min Act: -0.1700
Data Index: 2050588 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3887. Min Act: -0.1700
Data Index: 289196 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3573. Min Act: -0.1699
Data Index: 6962622 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3573. Min Act: -0.1677
Data Index: 152461 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3573. Min Act: -0.1700
Data Index: 2346477 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3573. Min Act: -0.1700
Data Index: 3858803 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3887. Min Act: -0.1697
Data Index: 4523047 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6393. Min Range: -3.6393
Max Act: 3.3573. Min Act: -0.1580
Data Index: 3958450 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19