Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.9714. Min Act: -0.1700
Data Index: 1124015 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.8776. Min Act: -0.1700
Data Index: 7275015 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.7526. Min Act: -0.1700
Data Index: 2464148 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.7526. Min Act: -0.1700
Data Index: 7691456 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.6276. Min Act: -0.1700
Data Index: 6715358 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5339. Min Act: -0.1700
Data Index: 8009787 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5339. Min Act: -0.1700
Data Index: 8051886 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5339. Min Act: -0.1700
Data Index: 772843 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.5026. Min Act: -0.1700
Data Index: 8418176 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.4714. Min Act: -0.1700
Data Index: 7190146 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.4714. Min Act: -0.1700
Data Index: 8107355 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3776. Min Act: -0.1700
Data Index: 3390265 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3776. Min Act: -0.1700
Data Index: 3248768 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.4089. Min Act: -0.1700
Data Index: 7532272 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3776. Min Act: -0.1700
Data Index: 7114049 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3776. Min Act: -0.1700
Data Index: 905239 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3776. Min Act: -0.1700
Data Index: 6505504 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 7877194 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 6310968 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9714. Min Range: -5.9714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 1555210 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19