Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2335 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.2991. Min Act: -0.1700
Data Index: 2860550 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.2991. Min Act: -0.1700
Data Index: 8802483 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.2678. Min Act: -0.1700
Data Index: 370187 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.1428. Min Act: -0.1700
Data Index: 5936576 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.1116. Min Act: -0.1700
Data Index: 2681047 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.1428. Min Act: -0.1700
Data Index: 8710898 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0803. Min Act: -0.1700
Data Index: 6590546 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0491. Min Act: -0.1700
Data Index: 5064521 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0491. Min Act: -0.1700
Data Index: 4878606 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0491. Min Act: -0.1700
Data Index: 1903400 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0491. Min Act: -0.1700
Data Index: 7535541 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0491. Min Act: -0.1700
Data Index: 1195874 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0491. Min Act: -0.1700
Data Index: 2384261 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0178. Min Act: -0.1700
Data Index: 4033748 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2991. Min Range: -4.2991
Max Act: 3.9865. Min Act: -0.1700
Data Index: 4898977 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0178. Min Act: -0.1700
Data Index: 2183206 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0178. Min Act: -0.1700
Data Index: 5358145 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2991. Min Range: -4.2991
Max Act: 4.0178. Min Act: -0.1700
Data Index: 1026090 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2991. Min Range: -4.2991
Max Act: 3.9865. Min Act: -0.1700
Data Index: 5040090 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2991. Min Range: -4.2991
Max Act: 3.9865. Min Act: -0.1700
Data Index: 6439839 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19