Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5708 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.1181. Min Act: -0.1700
Data Index: 519791 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 4655941 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 4003852 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1823009 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6806. Min Act: -0.1700
Data Index: 6465107 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6806. Min Act: -0.1700
Data Index: 5368683 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6806. Min Act: -0.1700
Data Index: 8375779 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6494. Min Act: -0.1700
Data Index: 3901577 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 688079 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 4520753 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 5730471 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5869. Min Act: -0.1700
Data Index: 8572205 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5556. Min Act: -0.1700
Data Index: 8068862 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5556. Min Act: -0.1700
Data Index: 3618046 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5869. Min Act: -0.1700
Data Index: 8622758 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5869. Min Act: -0.1700
Data Index: 6179955 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5869. Min Act: -0.1700
Data Index: 7505907 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5869. Min Act: -0.1700
Data Index: 4616175 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5556. Min Act: -0.1700
Data Index: 8271239 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5556. Min Act: -0.1700
Data Index: 3696678 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19