Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.6057. Min Act: -0.1700
Data Index: 2159107 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.4807. Min Act: -0.1700
Data Index: 2124149 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.3557. Min Act: -0.1700
Data Index: 2080684 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.1682. Min Act: -0.1700
Data Index: 6134977 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.1682. Min Act: -0.1700
Data Index: 8402564 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.1682. Min Act: -0.1700
Data Index: 6550066 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.1682. Min Act: -0.1700
Data Index: 4404089 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.1057. Min Act: -0.1700
Data Index: 7041899 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.0432. Min Act: -0.1700
Data Index: 5919648 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6057. Min Range: -8.6057
Max Act: 8.0432. Min Act: -0.1700
Data Index: 7661416 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.9807. Min Act: -0.1700
Data Index: 3842577 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.9807. Min Act: -0.1700
Data Index: 3069790 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.9182. Min Act: -0.1700
Data Index: 7782383 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.9182. Min Act: -0.1700
Data Index: 5595210 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.8557. Min Act: -0.1700
Data Index: 5502681 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.8557. Min Act: -0.1700
Data Index: 7466046 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.7932. Min Act: -0.1700
Data Index: 7481802 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.7932. Min Act: -0.1700
Data Index: 6570457 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.7932. Min Act: -0.1700
Data Index: 1814024 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6057. Min Range: -8.6057
Max Act: 7.7932. Min Act: -0.1700
Data Index: 2808957 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19