Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.5910. Min Act: -0.1700
Data Index: 7207511 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.4972. Min Act: -0.1700
Data Index: 7207519 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.4035. Min Act: -0.1700
Data Index: 7207523 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.3722. Min Act: -0.1700
Data Index: 6873042 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2785. Min Act: -0.1700
Data Index: 8211341 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 3772901 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 3584680 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 3745270 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2785. Min Act: -0.1700
Data Index: 8212600 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 4086079 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 6278092 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 3899894 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 606198 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1535. Min Act: -0.1700
Data Index: 6014166 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 1646073 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1535. Min Act: -0.1700
Data Index: 2569662 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 3815525 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 6522461 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0910. Min Act: -0.1700
Data Index: 2654229 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 2595596 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19