Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7585. Min Range: -7.7585
Max Act: 7.7585. Min Act: -0.1700
Data Index: 1135331 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7585. Min Range: -7.7585
Max Act: 7.4148. Min Act: -0.1700
Data Index: 3141811 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7585. Min Range: -7.7585
Max Act: 7.3523. Min Act: -0.1700
Data Index: 1531372 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7585. Min Range: -7.7585
Max Act: 7.0710. Min Act: -0.1700
Data Index: 7898616 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7585. Min Range: -7.7585
Max Act: 7.1023. Min Act: -0.1700
Data Index: 686371 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7585. Min Range: -7.7585
Max Act: 7.0710. Min Act: -0.1700
Data Index: 1768652 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7585. Min Range: -7.7585
Max Act: 7.0085. Min Act: -0.1700
Data Index: 8401722 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.9773. Min Act: -0.1700
Data Index: 6801538 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.9773. Min Act: -0.1700
Data Index: 4109920 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.9148. Min Act: -0.1700
Data Index: 4828876 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.9460. Min Act: -0.1700
Data Index: 4968044 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.8835. Min Act: -0.1700
Data Index: 6611852 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.8835. Min Act: -0.1700
Data Index: 5192331 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.8835. Min Act: -0.1700
Data Index: 4134893 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.8523. Min Act: -0.1700
Data Index: 794112 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.8835. Min Act: -0.1700
Data Index: 5081499 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.8835. Min Act: -0.1700
Data Index: 3177722 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.8210. Min Act: -0.1700
Data Index: 3480122 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.7585. Min Act: -0.1700
Data Index: 327900 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7585. Min Range: -7.7585
Max Act: 6.7898. Min Act: -0.1700
Data Index: 2154974 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19