Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1626 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2211. Min Range: -6.2211
Max Act: 6.2211. Min Act: -0.1700
Data Index: 5873780 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2211. Min Range: -6.2211
Max Act: 6.2211. Min Act: -0.1700
Data Index: 3868463 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2211. Min Range: -6.2211
Max Act: 6.1898. Min Act: -0.1700
Data Index: 3046129 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2211. Min Range: -6.2211
Max Act: 6.1586. Min Act: -0.1700
Data Index: 5643570 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2211. Min Range: -6.2211
Max Act: 6.1273. Min Act: -0.1700
Data Index: 3311681 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2211. Min Range: -6.2211
Max Act: 6.0648. Min Act: -0.1700
Data Index: 4770909 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2211. Min Range: -6.2211
Max Act: 6.0648. Min Act: -0.1700
Data Index: 7802436 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2211. Min Range: -6.2211
Max Act: 6.0023. Min Act: -0.1700
Data Index: 1541691 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.9711. Min Act: -0.1700
Data Index: 5236259 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.7523. Min Act: -0.1700
Data Index: 2220944 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.7523. Min Act: -0.1700
Data Index: 1733761 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.6898. Min Act: -0.1700
Data Index: 8648873 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.7211. Min Act: -0.1700
Data Index: 673987 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.7211. Min Act: -0.1700
Data Index: 1996747 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.7211. Min Act: -0.1700
Data Index: 931653 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.6898. Min Act: -0.1700
Data Index: 6558165 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.6898. Min Act: -0.1700
Data Index: 5950898 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.6898. Min Act: -0.1700
Data Index: 5842816 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.6898. Min Act: -0.1700
Data Index: 7864948 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2211. Min Range: -6.2211
Max Act: 5.6586. Min Act: -0.1700
Data Index: 8593249 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19