Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6816. Min Range: -9.6816
Max Act: 9.6816. Min Act: -0.1700
Data Index: 5746660 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6816. Min Range: -9.6816
Max Act: 9.5566. Min Act: -0.1700
Data Index: 1447753 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6816. Min Range: -9.6816
Max Act: 9.4941. Min Act: -0.1700
Data Index: 1447752 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6816. Min Range: -9.6816
Max Act: 9.4316. Min Act: -0.1700
Data Index: 7434517 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6816. Min Range: -9.6816
Max Act: 9.1816. Min Act: -0.1700
Data Index: 5746658 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6816. Min Range: -9.6816
Max Act: 9.0566. Min Act: -0.1700
Data Index: 4802607 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.9941. Min Act: -0.1700
Data Index: 47826 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.9941. Min Act: -0.1700
Data Index: 3696072 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6816. Min Range: -9.6816
Max Act: 9.0566. Min Act: -0.1700
Data Index: 667358 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.9941. Min Act: -0.1700
Data Index: 7322024 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.9316. Min Act: -0.1700
Data Index: 4014029 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.9316. Min Act: -0.1700
Data Index: 6279275 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.8691. Min Act: -0.1700
Data Index: 5015868 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.9316. Min Act: -0.1700
Data Index: 3009029 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.8691. Min Act: -0.1700
Data Index: 2069838 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.8691. Min Act: -0.1700
Data Index: 741205 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.8691. Min Act: -0.1700
Data Index: 121426 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.8691. Min Act: -0.1700
Data Index: 443998 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.8691. Min Act: -0.1700
Data Index: 7008913 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6816. Min Range: -9.6816
Max Act: 8.8066. Min Act: -0.1700
Data Index: 4277770 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19