Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3781 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.8031. Min Act: -0.1700
Data Index: 171233 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.7553. Min Act: -0.1700
Data Index: 4677056 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.7073. Min Act: -0.1700
Data Index: 7522948 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6913. Min Act: -0.1700
Data Index: 5080993 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6753. Min Act: -0.1700
Data Index: 5433499 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6432. Min Act: -0.1700
Data Index: 6409471 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6272. Min Act: -0.1700
Data Index: 3856551 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6432. Min Act: -0.1700
Data Index: 810605 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6272. Min Act: -0.1700
Data Index: 1819172 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6272. Min Act: -0.1700
Data Index: 550289 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6272. Min Act: -0.1700
Data Index: 7447769 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6272. Min Act: -0.1700
Data Index: 5303036 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6111. Min Act: -0.1700
Data Index: 137197 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6111. Min Act: -0.1700
Data Index: 1584419 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.5950. Min Act: -0.1700
Data Index: 4662248 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6111. Min Act: -0.1700
Data Index: 2788419 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6111. Min Act: -0.1700
Data Index: 5040487 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6111. Min Act: -0.1700
Data Index: 5441845 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.5950. Min Act: -0.1700
Data Index: 3368165 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8031. Min Range: -2.8031
Max Act: 2.6111. Min Act: -0.1700
Data Index: 4446003 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19