Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1156 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3930. Min Act: -0.1700
Data Index: 4862788 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3930. Min Act: -0.1700
Data Index: 8789092 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3930. Min Act: -0.1700
Data Index: 2454034 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3618. Min Act: -0.1700
Data Index: 3987273 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3930. Min Act: -0.1700
Data Index: 3326766 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3930. Min Act: -0.1700
Data Index: 6048271 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3305. Min Act: -0.1700
Data Index: 5263809 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3618. Min Act: -0.1700
Data Index: 5723787 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.3305. Min Act: -0.1700
Data Index: 4567969 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2680. Min Act: -0.1700
Data Index: 829643 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2993. Min Act: -0.1700
Data Index: 160453 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2993. Min Act: -0.1700
Data Index: 7638147 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2993. Min Act: -0.1700
Data Index: 6391540 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2993. Min Act: -0.1700
Data Index: 3630730 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2680. Min Act: -0.1700
Data Index: 5628105 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2680. Min Act: -0.1700
Data Index: 4227327 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2680. Min Act: -0.1700
Data Index: 109223 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2993. Min Act: -0.1700
Data Index: 4698336 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2680. Min Act: -0.1700
Data Index: 3850847 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3930. Min Range: -5.3930
Max Act: 5.2993. Min Act: -0.1700
Data Index: 3189635 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19