Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4385 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1136. Min Range: -5.1136
Max Act: 5.1136. Min Act: -0.1700
Data Index: 4060052 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.8636. Min Act: -0.1700
Data Index: 3679573 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.8636. Min Act: -0.1700
Data Index: 1898532 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.8323. Min Act: -0.1700
Data Index: 6819268 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.8323. Min Act: -0.1700
Data Index: 801273 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.7698. Min Act: -0.1700
Data Index: 1689311 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.7386. Min Act: -0.1700
Data Index: 3409681 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.7073. Min Act: -0.1700
Data Index: 644112 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.7073. Min Act: -0.1700
Data Index: 6903692 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.7073. Min Act: -0.1700
Data Index: 3737569 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.7073. Min Act: -0.1700
Data Index: 6154768 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6448. Min Act: -0.1700
Data Index: 3355195 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6761. Min Act: -0.1700
Data Index: 378375 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6761. Min Act: -0.1700
Data Index: 7103446 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6761. Min Act: -0.1700
Data Index: 3709282 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6761. Min Act: -0.1700
Data Index: 452766 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6448. Min Act: -0.1700
Data Index: 1845988 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6448. Min Act: -0.1700
Data Index: 5069083 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6448. Min Act: -0.1700
Data Index: 2829976 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1136. Min Range: -5.1136
Max Act: 4.6136. Min Act: -0.1700
Data Index: 6075683 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19