Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.6066. Min Act: -0.1700
Data Index: 3982367 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.4816. Min Act: -0.1700
Data Index: 3506343 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.2316. Min Act: -0.1700
Data Index: 1381748 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.2316. Min Act: -0.1700
Data Index: 392175 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.2004. Min Act: -0.1700
Data Index: 3306744 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0753. Min Act: -0.1700
Data Index: 7383216 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.1066. Min Act: -0.1700
Data Index: 4795097 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0753. Min Act: -0.1700
Data Index: 4313528 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0128. Min Act: -0.1700
Data Index: 2545264 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0128. Min Act: -0.1700
Data Index: 4302112 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0128. Min Act: -0.1700
Data Index: 472010 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0128. Min Act: -0.1700
Data Index: 3494057 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0128. Min Act: -0.1700
Data Index: 2417552 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0128. Min Act: -0.1700
Data Index: 1579787 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6066. Min Range: -4.6066
Max Act: 4.0128. Min Act: -0.1700
Data Index: 867693 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6066. Min Range: -4.6066
Max Act: 3.9816. Min Act: -0.1700
Data Index: 5355231 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6066. Min Range: -4.6066
Max Act: 3.9816. Min Act: -0.1700
Data Index: 2861086 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6066. Min Range: -4.6066
Max Act: 3.9816. Min Act: -0.1700
Data Index: 7471936 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6066. Min Range: -4.6066
Max Act: 3.9190. Min Act: -0.1700
Data Index: 5524730 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6066. Min Range: -4.6066
Max Act: 3.9503. Min Act: -0.1700
Data Index: 7099727 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19