Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.8462. Min Act: -0.1700
Data Index: 8329005 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.7837. Min Act: -0.1700
Data Index: 511564 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.6899. Min Act: -0.1700
Data Index: 7634036 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.6899. Min Act: -0.1700
Data Index: 2204444 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.5962. Min Act: -0.1700
Data Index: 6619238 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.5962. Min Act: -0.1700
Data Index: 1224140 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.5962. Min Act: -0.1700
Data Index: 4683291 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.5962. Min Act: -0.1700
Data Index: 1203822 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.5649. Min Act: -0.1700
Data Index: 3203308 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.5649. Min Act: -0.1700
Data Index: 4790225 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.4712. Min Act: -0.1700
Data Index: 4319973 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.4399. Min Act: -0.1700
Data Index: 1736166 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.4399. Min Act: -0.1700
Data Index: 4406114 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.4087. Min Act: -0.1700
Data Index: 5278262 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.4087. Min Act: -0.1700
Data Index: 3520282 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.4087. Min Act: -0.1700
Data Index: 3145187 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.4087. Min Act: -0.1700
Data Index: 2384922 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.3774. Min Act: -0.1700
Data Index: 3798067 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.3774. Min Act: -0.1700
Data Index: 3159760 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8462. Min Range: -5.8462
Max Act: 5.3774. Min Act: -0.1700
Data Index: 1151530 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19