Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3297 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1553. Min Range: -7.1553
Max Act: 7.1553. Min Act: -0.1700
Data Index: 2209612 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1553. Min Range: -7.1553
Max Act: 7.0303. Min Act: -0.1700
Data Index: 8188591 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.9678. Min Act: -0.1700
Data Index: 2577586 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.9053. Min Act: -0.1700
Data Index: 4702962 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.9365. Min Act: -0.1700
Data Index: 7841411 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.8115. Min Act: -0.1700
Data Index: 29999 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.7490. Min Act: -0.1700
Data Index: 4023035 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6460198 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.7178. Min Act: -0.1700
Data Index: 509084 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6306647 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6246914 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.6553. Min Act: -0.1700
Data Index: 3385752 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.6553. Min Act: -0.1700
Data Index: 4105217 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.6553. Min Act: -0.1700
Data Index: 2727318 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.6553. Min Act: -0.1700
Data Index: 3202995 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.5928. Min Act: -0.1700
Data Index: 838915 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.5303. Min Act: -0.1700
Data Index: 3888698 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.5303. Min Act: -0.1700
Data Index: 1872204 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.4990. Min Act: -0.1700
Data Index: 7895915 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1553. Min Range: -7.1553
Max Act: 6.5303. Min Act: -0.1700
Data Index: 738690 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19