Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1846 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.3609. Min Act: -0.1700
Data Index: 1567157 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.2671. Min Act: -0.1700
Data Index: 8007353 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.2671. Min Act: -0.1700
Data Index: 3153876 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.2046. Min Act: -0.1700
Data Index: 4339886 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.1734. Min Act: -0.1700
Data Index: 183402 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.2046. Min Act: -0.1700
Data Index: 6091087 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.1421. Min Act: -0.1700
Data Index: 3659195 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.0484. Min Act: -0.1700
Data Index: 4952521 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.0796. Min Act: -0.1700
Data Index: 8348993 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.0796. Min Act: -0.1700
Data Index: 505835 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.0171. Min Act: -0.1700
Data Index: 4150703 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.0171. Min Act: -0.1700
Data Index: 1082861 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.0171. Min Act: -0.1700
Data Index: 2972587 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.0171. Min Act: -0.1700
Data Index: 5789649 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3609. Min Range: -5.3609
Max Act: 5.0171. Min Act: -0.1700
Data Index: 2938129 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3609. Min Range: -5.3609
Max Act: 4.9859. Min Act: -0.1700
Data Index: 2011728 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3609. Min Range: -5.3609
Max Act: 4.9859. Min Act: -0.1700
Data Index: 5744259 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3609. Min Range: -5.3609
Max Act: 4.9859. Min Act: -0.1700
Data Index: 8026825 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3609. Min Range: -5.3609
Max Act: 4.9546. Min Act: -0.1700
Data Index: 2989589 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3609. Min Range: -5.3609
Max Act: 4.9234. Min Act: -0.1700
Data Index: 7486345 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19