Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4052. Min Range: -6.4052
Max Act: 6.4052. Min Act: -0.1700
Data Index: 3989987 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.9989. Min Act: -0.1700
Data Index: 7808906 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.7802. Min Act: -0.1700
Data Index: 2131037 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.5927. Min Act: -0.1700
Data Index: 301956 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.5927. Min Act: -0.1700
Data Index: 7854279 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.5614. Min Act: -0.1700
Data Index: 1043981 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.5302. Min Act: -0.1700
Data Index: 2682284 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4989. Min Act: -0.1700
Data Index: 6485348 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4989. Min Act: -0.1700
Data Index: 5247144 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4677. Min Act: -0.1700
Data Index: 1262256 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4677. Min Act: -0.1700
Data Index: 2705536 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4677. Min Act: -0.1700
Data Index: 6180175 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4364. Min Act: -0.1700
Data Index: 641206 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4364. Min Act: -0.1700
Data Index: 4964848 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4052. Min Act: -0.1700
Data Index: 6705979 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4364. Min Act: -0.1700
Data Index: 418180 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4364. Min Act: -0.1700
Data Index: 7518589 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4052. Min Act: -0.1700
Data Index: 7089323 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.4052. Min Act: -0.1700
Data Index: 4574644 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4052. Min Range: -6.4052
Max Act: 5.3739. Min Act: -0.1700
Data Index: 4221226 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19