Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2044 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.7523. Min Act: -0.1700
Data Index: 6551949 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.7044. Min Act: -0.1700
Data Index: 5572305 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6884. Min Act: -0.1700
Data Index: 8482736 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6563. Min Act: -0.1700
Data Index: 969942 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6723. Min Act: -0.1700
Data Index: 5493028 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6563. Min Act: -0.1700
Data Index: 5572295 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6242. Min Act: -0.1700
Data Index: 3691042 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6403. Min Act: -0.1700
Data Index: 6097535 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6403. Min Act: -0.1700
Data Index: 5203312 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6242. Min Act: -0.1700
Data Index: 6063623 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6242. Min Act: -0.1700
Data Index: 4528979 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6081. Min Act: -0.1700
Data Index: 8366041 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6081. Min Act: -0.1700
Data Index: 6944625 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6081. Min Act: -0.1700
Data Index: 1566219 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.6081. Min Act: -0.1700
Data Index: 6063624 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.5920. Min Act: -0.1700
Data Index: 8302928 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.5920. Min Act: -0.1700
Data Index: 3357145 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.5920. Min Act: -0.1700
Data Index: 756617 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.5920. Min Act: -0.1700
Data Index: 6689284 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7523. Min Range: -2.7523
Max Act: 2.5920. Min Act: -0.1700
Data Index: 284474 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19