Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1754 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.5685. Min Act: -0.1700
Data Index: 8747026 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.5685. Min Act: -0.1700
Data Index: 8283504 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.5373. Min Act: -0.1700
Data Index: 3727798 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.5060. Min Act: -0.1700
Data Index: 297098 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.5060. Min Act: -0.1700
Data Index: 7371572 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.5060. Min Act: -0.1700
Data Index: 6923483 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.5060. Min Act: -0.1700
Data Index: 4188751 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4748. Min Act: -0.1700
Data Index: 2176983 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4748. Min Act: -0.1700
Data Index: 6766178 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4748. Min Act: -0.1700
Data Index: 392861 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4435. Min Act: -0.1700
Data Index: 8156228 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4435. Min Act: -0.1700
Data Index: 979689 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4435. Min Act: -0.1700
Data Index: 7323894 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4435. Min Act: -0.1700
Data Index: 5444941 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4123. Min Act: -0.1700
Data Index: 7391671 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4123. Min Act: -0.1700
Data Index: 95247 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.3810. Min Act: -0.1700
Data Index: 1501064 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.4123. Min Act: -0.1700
Data Index: 6476122 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.3498. Min Act: -0.1700
Data Index: 2662558 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5685. Min Range: -5.5685
Max Act: 5.3185. Min Act: -0.1700
Data Index: 8278482 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19