Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.2727. Min Act: -0.1700
Data Index: 3280181 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.2415. Min Act: -0.1700
Data Index: 5703735 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.2102. Min Act: -0.1700
Data Index: 1614614 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.2102. Min Act: -0.1700
Data Index: 480932 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.2102. Min Act: -0.1700
Data Index: 4517049 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.1477. Min Act: -0.1700
Data Index: 3683541 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.1165. Min Act: -0.1700
Data Index: 8219308 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0852. Min Act: -0.1700
Data Index: 138454 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0852. Min Act: -0.1700
Data Index: 7688295 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0540. Min Act: -0.1700
Data Index: 3443661 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0540. Min Act: -0.1700
Data Index: 1224501 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0540. Min Act: -0.1700
Data Index: 4494480 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0540. Min Act: -0.1700
Data Index: 7714833 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0540. Min Act: -0.1700
Data Index: 3193958 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0227. Min Act: -0.1700
Data Index: 7177746 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0540. Min Act: -0.1700
Data Index: 1761649 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0540. Min Act: -0.1700
Data Index: 4510949 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0227. Min Act: -0.1700
Data Index: 1928400 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0227. Min Act: -0.1700
Data Index: 1354996 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2727. Min Range: -5.2727
Max Act: 5.0227. Min Act: -0.1700
Data Index: 6155937 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19