Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1251 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1741. Min Range: -5.1741
Max Act: 5.1741. Min Act: -0.1700
Data Index: 7386033 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1741. Min Range: -5.1741
Max Act: 5.0804. Min Act: -0.1700
Data Index: 2920088 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1741. Min Range: -5.1741
Max Act: 5.0491. Min Act: -0.1700
Data Index: 3991071 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.9554. Min Act: -0.1700
Data Index: 7267744 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.9554. Min Act: -0.1700
Data Index: 7860025 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.9554. Min Act: -0.1700
Data Index: 1883643 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5337514 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.9241. Min Act: -0.1700
Data Index: 4799838 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.8929. Min Act: -0.1700
Data Index: 2942758 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.8616. Min Act: -0.1700
Data Index: 2084414 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.8616. Min Act: -0.1700
Data Index: 4696607 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.8304. Min Act: -0.1700
Data Index: 8061909 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.8304. Min Act: -0.1700
Data Index: 3308938 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.7991. Min Act: -0.1700
Data Index: 102893 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.7991. Min Act: -0.1700
Data Index: 1186554 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.7991. Min Act: -0.1700
Data Index: 7365612 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.7991. Min Act: -0.1700
Data Index: 3615296 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.7679. Min Act: -0.1700
Data Index: 6934884 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.7679. Min Act: -0.1700
Data Index: 3543093 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1741. Min Range: -5.1741
Max Act: 4.7679. Min Act: -0.1700
Data Index: 2495681 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19