Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1607. Min Range: -9.1607
Max Act: 9.1607. Min Act: -0.1700
Data Index: 7393806 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1607. Min Range: -9.1607
Max Act: 9.1607. Min Act: -0.1700
Data Index: 6397698 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1607. Min Range: -9.1607
Max Act: 9.0982. Min Act: -0.1700
Data Index: 6057157 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1607. Min Range: -9.1607
Max Act: 9.0357. Min Act: -0.1700
Data Index: 2579061 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.9732. Min Act: -0.1700
Data Index: 2305008 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.9732. Min Act: -0.1700
Data Index: 4087930 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.9107. Min Act: -0.1700
Data Index: 2325990 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.9107. Min Act: -0.1700
Data Index: 591854 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.9107. Min Act: -0.1700
Data Index: 8269194 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.8482. Min Act: -0.1700
Data Index: 4223126 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.8482. Min Act: -0.1700
Data Index: 3383641 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.8482. Min Act: -0.1700
Data Index: 4282001 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.8482. Min Act: -0.1700
Data Index: 8006777 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.7857. Min Act: -0.1700
Data Index: 552191 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.7857. Min Act: -0.1700
Data Index: 6497017 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.7857. Min Act: -0.1700
Data Index: 334213 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.7857. Min Act: -0.1700
Data Index: 7451910 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.7232. Min Act: -0.1700
Data Index: 935953 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.7857. Min Act: -0.1700
Data Index: 920994 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1607. Min Range: -9.1607
Max Act: 8.7232. Min Act: -0.1700
Data Index: 4046462 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19