Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1030. Min Range: -6.1030
Max Act: 6.1030. Min Act: -0.1700
Data Index: 963645 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1030. Min Range: -6.1030
Max Act: 6.0405. Min Act: -0.1700
Data Index: 4111188 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.7905. Min Act: -0.1700
Data Index: 5429481 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.7592. Min Act: -0.1700
Data Index: 504525 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.6342. Min Act: -0.1700
Data Index: 5899530 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.6030. Min Act: -0.1700
Data Index: 949932 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.5092. Min Act: -0.1700
Data Index: 6592304 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.5717. Min Act: -0.1700
Data Index: 5849849 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.5405. Min Act: -0.1700
Data Index: 5942091 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.5092. Min Act: -0.1700
Data Index: 8539690 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.5092. Min Act: -0.1700
Data Index: 215789 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.5092. Min Act: -0.1700
Data Index: 1569392 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.5092. Min Act: -0.1700
Data Index: 2126707 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.4780. Min Act: -0.1700
Data Index: 86284 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.4467. Min Act: -0.1700
Data Index: 7973199 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.4467. Min Act: -0.1700
Data Index: 1690527 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.3842. Min Act: -0.1700
Data Index: 1217464 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.3842. Min Act: -0.1700
Data Index: 7508449 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.3842. Min Act: -0.1700
Data Index: 7997936 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1030. Min Range: -6.1030
Max Act: 5.3530. Min Act: -0.1700
Data Index: 5836103 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19