Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2239 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0564. Min Range: -5.0564
Max Act: 5.0564. Min Act: -0.1700
Data Index: 1812676 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.9314. Min Act: -0.1700
Data Index: 6292362 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.9002. Min Act: -0.1700
Data Index: 6429577 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.8689. Min Act: -0.1700
Data Index: 6279326 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.8689. Min Act: -0.1700
Data Index: 206352 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.8377. Min Act: -0.1700
Data Index: 7201943 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.8377. Min Act: -0.1700
Data Index: 2968681 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.7127. Min Act: -0.1700
Data Index: 6147770 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.7127. Min Act: -0.1700
Data Index: 1681901 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.6814. Min Act: -0.1700
Data Index: 7300159 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.6814. Min Act: -0.1700
Data Index: 4653883 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.6189. Min Act: -0.1700
Data Index: 526327 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.6502. Min Act: -0.1700
Data Index: 4507055 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.6189. Min Act: -0.1700
Data Index: 8632360 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.6189. Min Act: -0.1700
Data Index: 300088 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.6189. Min Act: -0.1700
Data Index: 5623715 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.5877. Min Act: -0.1700
Data Index: 4798429 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.5564. Min Act: -0.1700
Data Index: 2036860 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.5564. Min Act: -0.1700
Data Index: 2036859 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0564. Min Range: -5.0564
Max Act: 4.5564. Min Act: -0.1700
Data Index: 5776915 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19