Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.2231. Min Act: -0.1700
Data Index: 6598256 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.1918. Min Act: -0.1698
Data Index: 1127685 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.1293. Min Act: -0.1700
Data Index: 7471389 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.1293. Min Act: -0.1700
Data Index: 607258 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0981. Min Act: -0.1699
Data Index: 8288567 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.1293. Min Act: -0.1698
Data Index: 6467535 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0668. Min Act: -0.1700
Data Index: 6815549 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0668. Min Act: -0.1700
Data Index: 106202 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0668. Min Act: -0.1700
Data Index: 1501597 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0668. Min Act: -0.1700
Data Index: 5110908 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0668. Min Act: -0.1700
Data Index: 538816 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0668. Min Act: -0.1700
Data Index: 5760538 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0043. Min Act: -0.1700
Data Index: 1624239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0356. Min Act: -0.1700
Data Index: 4818371 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0356. Min Act: -0.1700
Data Index: 3701460 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0356. Min Act: -0.1700
Data Index: 3939835 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0356. Min Act: -0.1700
Data Index: 7726813 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0356. Min Act: -0.1700
Data Index: 7738934 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0356. Min Act: -0.1700
Data Index: 463652 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2231. Min Range: -5.2231
Max Act: 5.0043. Min Act: -0.1700
Data Index: 5662709 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19