Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2089 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.4120. Min Act: -0.1700
Data Index: 4720382 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.4120. Min Act: -0.1700
Data Index: 4836658 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.2870. Min Act: -0.1700
Data Index: 6325405 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.3183. Min Act: -0.1700
Data Index: 248454 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.2870. Min Act: -0.1700
Data Index: 5465307 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.2245. Min Act: -0.1700
Data Index: 5718835 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.1933. Min Act: -0.1700
Data Index: 2993866 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.1933. Min Act: -0.1700
Data Index: 4169190 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0995. Min Act: -0.1700
Data Index: 414904 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0995. Min Act: -0.1700
Data Index: 5509527 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0995. Min Act: -0.1700
Data Index: 3442494 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0683. Min Act: -0.1700
Data Index: 5575261 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0683. Min Act: -0.1700
Data Index: 5722219 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0370. Min Act: -0.1700
Data Index: 2168509 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0370. Min Act: -0.1700
Data Index: 651047 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0370. Min Act: -0.1700
Data Index: 3125504 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0370. Min Act: -0.1700
Data Index: 1620482 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0370. Min Act: -0.1700
Data Index: 5936497 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4120. Min Range: -6.4120
Max Act: 5.9745. Min Act: -0.1700
Data Index: 1459411 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4120. Min Range: -6.4120
Max Act: 6.0058. Min Act: -0.1700
Data Index: 5304746 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19