Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.7675. Min Act: -0.1700
Data Index: 6454206 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.7206. Min Act: -0.1700
Data Index: 8169873 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.6580. Min Act: -0.1700
Data Index: 3624951 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.6423. Min Act: -0.1700
Data Index: 8160775 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.6423. Min Act: -0.1700
Data Index: 5441815 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5328. Min Act: -0.1700
Data Index: 8731705 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5171. Min Act: -0.1700
Data Index: 8189484 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.5171. Min Act: -0.1700
Data Index: 740485 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4858. Min Act: -0.1700
Data Index: 1005430 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4858. Min Act: -0.1700
Data Index: 608523 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4858. Min Act: -0.1700
Data Index: 6132792 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4858. Min Act: -0.1700
Data Index: 4641265 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4858. Min Act: -0.1700
Data Index: 3742813 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4701. Min Act: -0.1700
Data Index: 3155964 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4701. Min Act: -0.1700
Data Index: 1701711 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4545. Min Act: -0.1700
Data Index: 8391318 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4701. Min Act: -0.1700
Data Index: 5854319 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4388. Min Act: -0.1700
Data Index: 4672195 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4388. Min Act: -0.1700
Data Index: 1519092 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7675. Min Range: -3.7675
Max Act: 3.4545. Min Act: -0.1700
Data Index: 371193 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19