Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5433 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.6242. Min Act: -0.1700
Data Index: 3289465 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.6242. Min Act: -0.1700
Data Index: 4842604 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.6242. Min Act: -0.1700
Data Index: 1718292 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4680. Min Act: -0.1700
Data Index: 2217574 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4680. Min Act: -0.1700
Data Index: 5651326 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4680. Min Act: -0.1700
Data Index: 4923312 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4680. Min Act: -0.1700
Data Index: 734777 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4680. Min Act: -0.1700
Data Index: 7400327 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4367. Min Act: -0.1700
Data Index: 4039651 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4367. Min Act: -0.1700
Data Index: 2210930 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4055. Min Act: -0.1700
Data Index: 8168647 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4055. Min Act: -0.1700
Data Index: 4219363 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4055. Min Act: -0.1700
Data Index: 4219362 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.3742. Min Act: -0.1700
Data Index: 1598602 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.3430. Min Act: -0.1700
Data Index: 2168319 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.3430. Min Act: -0.1700
Data Index: 2573753 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.3430. Min Act: -0.1700
Data Index: 1610246 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.3117. Min Act: -0.1700
Data Index: 593621 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.2805. Min Act: -0.1700
Data Index: 1610245 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.3117. Min Act: -0.1700
Data Index: 1122900 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19