Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.4766. Min Act: -0.1700
Data Index: 3889007 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.4295. Min Act: -0.1700
Data Index: 8346638 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.3355. Min Act: -0.1700
Data Index: 2106621 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.2255. Min Act: -0.1700
Data Index: 8298812 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.1784. Min Act: -0.1700
Data Index: 6339095 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.1784. Min Act: -0.1700
Data Index: 1494150 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.1784. Min Act: -0.1700
Data Index: 651701 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.1469. Min Act: -0.1700
Data Index: 5994923 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.1469. Min Act: -0.1700
Data Index: 1122195 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.1469. Min Act: -0.1700
Data Index: 5977536 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0996. Min Act: -0.1700
Data Index: 3913363 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.1154. Min Act: -0.1700
Data Index: 2793302 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0996. Min Act: -0.1700
Data Index: 7285349 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0839. Min Act: -0.1700
Data Index: 7245160 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0839. Min Act: -0.1700
Data Index: 4600365 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0996. Min Act: -0.1700
Data Index: 4111123 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0839. Min Act: -0.1700
Data Index: 8283482 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0681. Min Act: -0.1700
Data Index: 5918950 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0681. Min Act: -0.1700
Data Index: 1852675 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4766. Min Range: -3.4766
Max Act: 3.0523. Min Act: -0.1700
Data Index: 5125942 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19