Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3886 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.8586. Min Act: -0.1700
Data Index: 4073156 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.8273. Min Act: -0.1700
Data Index: 7207826 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.8586. Min Act: -0.1700
Data Index: 5473926 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.8273. Min Act: -0.1700
Data Index: 1922994 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.8273. Min Act: -0.1700
Data Index: 5610666 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7961. Min Act: -0.1700
Data Index: 1049143 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7961. Min Act: -0.1700
Data Index: 2718318 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7648. Min Act: -0.1700
Data Index: 2400268 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7648. Min Act: -0.1700
Data Index: 3159454 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7648. Min Act: -0.1700
Data Index: 3523833 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7336. Min Act: -0.1700
Data Index: 1047173 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7023. Min Act: -0.1700
Data Index: 8258839 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7023. Min Act: -0.1700
Data Index: 4100489 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7336. Min Act: -0.1700
Data Index: 3773995 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7023. Min Act: -0.1700
Data Index: 6404037 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.7023. Min Act: -0.1700
Data Index: 5233501 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.6711. Min Act: -0.1700
Data Index: 1741434 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.6398. Min Act: -0.1700
Data Index: 8758127 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.6711. Min Act: -0.1700
Data Index: 4896857 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8586. Min Range: -4.8586
Max Act: 4.6398. Min Act: -0.1700
Data Index: 7021192 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19