Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4257 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4482. Min Range: -9.4482
Max Act: 9.4482. Min Act: -0.1700
Data Index: 258952 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4482. Min Range: -9.4482
Max Act: 9.3857. Min Act: -0.1700
Data Index: 203606 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4482. Min Range: -9.4482
Max Act: 9.2607. Min Act: -0.1700
Data Index: 3864252 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4482. Min Range: -9.4482
Max Act: 9.1357. Min Act: -0.1700
Data Index: 5165463 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4482. Min Range: -9.4482
Max Act: 9.1357. Min Act: -0.1700
Data Index: 3603086 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4482. Min Range: -9.4482
Max Act: 9.0732. Min Act: -0.1700
Data Index: 4712245 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4482. Min Range: -9.4482
Max Act: 9.0107. Min Act: -0.1700
Data Index: 5624440 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4482. Min Range: -9.4482
Max Act: 9.0107. Min Act: -0.1700
Data Index: 6231042 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.9482. Min Act: -0.1700
Data Index: 1925819 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.9482. Min Act: -0.1700
Data Index: 2792974 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.9482. Min Act: -0.1700
Data Index: 6046059 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.8857. Min Act: -0.1700
Data Index: 1310838 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.8232. Min Act: -0.1700
Data Index: 8096028 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.8232. Min Act: -0.1700
Data Index: 7259199 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.8232. Min Act: -0.1700
Data Index: 932769 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.8232. Min Act: -0.1700
Data Index: 5199827 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.8232. Min Act: -0.1700
Data Index: 3183922 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.7607. Min Act: -0.1700
Data Index: 2792420 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.7607. Min Act: -0.1700
Data Index: 2281410 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4482. Min Range: -9.4482
Max Act: 8.7607. Min Act: -0.1700
Data Index: 7943909 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19