Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3844 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.6376. Min Act: -0.1700
Data Index: 6097002 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.5439. Min Act: -0.1700
Data Index: 2647727 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.5126. Min Act: -0.1700
Data Index: 4528854 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.4814. Min Act: -0.1700
Data Index: 5672236 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.4814. Min Act: -0.1700
Data Index: 1230267 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.4501. Min Act: -0.1700
Data Index: 4528852 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.4501. Min Act: -0.1700
Data Index: 7590003 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.4189. Min Act: -0.1700
Data Index: 6658527 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.4189. Min Act: -0.1700
Data Index: 5392528 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3876. Min Act: -0.1700
Data Index: 6499585 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3876. Min Act: -0.1700
Data Index: 2254017 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3876. Min Act: -0.1700
Data Index: 7232714 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3876. Min Act: -0.1700
Data Index: 5710850 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3876. Min Act: -0.1700
Data Index: 7161640 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3564. Min Act: -0.1700
Data Index: 4321282 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3564. Min Act: -0.1700
Data Index: 3263225 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3564. Min Act: -0.1700
Data Index: 502422 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3564. Min Act: -0.1700
Data Index: 6442434 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3564. Min Act: -0.1700
Data Index: 6319053 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6376. Min Range: -5.6376
Max Act: 5.3564. Min Act: -0.1700
Data Index: 7620472 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19