Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5334 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0010. Min Range: -7.0010
Max Act: 7.0010. Min Act: -0.1700
Data Index: 1726430 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 91170 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 7712237 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 7137054 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.9385. Min Act: -0.1693
Data Index: 6277131 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 3622008 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8760. Min Act: -0.1700
Data Index: 5919850 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8760. Min Act: -0.1700
Data Index: 4626739 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8760. Min Act: -0.1698
Data Index: 3711861 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8135. Min Act: -0.1700
Data Index: 5579352 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8135. Min Act: -0.1700
Data Index: 1397439 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8135. Min Act: -0.1700
Data Index: 2440621 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8135. Min Act: -0.1700
Data Index: 1571301 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8135. Min Act: -0.1700
Data Index: 2367280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8135. Min Act: -0.1700
Data Index: 2317880 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8135. Min Act: -0.1700
Data Index: 8373688 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.8135. Min Act: -0.1700
Data Index: 4490401 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.7510. Min Act: -0.1700
Data Index: 819696 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.7510. Min Act: -0.1700
Data Index: 4330311 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0010. Min Range: -7.0010
Max Act: 6.7510. Min Act: -0.1700
Data Index: 388470 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19