Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.5588. Min Act: -0.1700
Data Index: 3744497 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.4963. Min Act: -0.1700
Data Index: 1593606 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.4651. Min Act: -0.1700
Data Index: 272701 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.4651. Min Act: -0.1700
Data Index: 1368598 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.4026. Min Act: -0.1700
Data Index: 2752398 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.4026. Min Act: -0.1700
Data Index: 302968 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.4026. Min Act: -0.1700
Data Index: 3343431 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.3713. Min Act: -0.1700
Data Index: 1791099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.3401. Min Act: -0.1700
Data Index: 8149062 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.3401. Min Act: -0.1700
Data Index: 6811906 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.3401. Min Act: -0.1700
Data Index: 7107946 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.3088. Min Act: -0.1700
Data Index: 7677061 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.2776. Min Act: -0.1700
Data Index: 1697378 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.2776. Min Act: -0.1700
Data Index: 2015931 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.2776. Min Act: -0.1700
Data Index: 4076266 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.2776. Min Act: -0.1700
Data Index: 7770240 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.2776. Min Act: -0.1700
Data Index: 46808 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.2776. Min Act: -0.1700
Data Index: 2632391 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.2776. Min Act: -0.1700
Data Index: 4027190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5588. Min Range: -4.5588
Max Act: 4.2776. Min Act: -0.1700
Data Index: 1597285 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19