Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 936 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.5910. Min Act: -0.1700
Data Index: 8789379 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.4972. Min Act: -0.1700
Data Index: 6868933 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.4035. Min Act: -0.1700
Data Index: 4144409 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.4035. Min Act: -0.1700
Data Index: 3932287 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.3410. Min Act: -0.1700
Data Index: 2644499 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.3410. Min Act: -0.1700
Data Index: 6604256 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.3097. Min Act: -0.1700
Data Index: 4642010 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.3097. Min Act: -0.1700
Data Index: 6745696 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.3097. Min Act: -0.1700
Data Index: 8352419 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2785. Min Act: -0.1700
Data Index: 2731990 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2785. Min Act: -0.1700
Data Index: 5814582 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 4072530 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 8346936 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 7695999 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 6309358 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 3065327 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2472. Min Act: -0.1700
Data Index: 4676493 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1847. Min Act: -0.1700
Data Index: 6170430 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 430080 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1847. Min Act: -0.1700
Data Index: 3069391 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19