Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2637. Min Range: -7.2637
Max Act: 7.2637. Min Act: -0.1700
Data Index: 565795 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.9825. Min Act: -0.1700
Data Index: 3251097 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.9200. Min Act: -0.1700
Data Index: 6344414 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.7950. Min Act: -0.1700
Data Index: 416279 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.7637. Min Act: -0.1700
Data Index: 306067 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.7325. Min Act: -0.1700
Data Index: 2815977 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.7012. Min Act: -0.1700
Data Index: 8518907 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.7012. Min Act: -0.1700
Data Index: 4475855 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.6700. Min Act: -0.1700
Data Index: 3899030 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.6387. Min Act: -0.1700
Data Index: 1088062 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.6387. Min Act: -0.1700
Data Index: 1059260 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.6075. Min Act: -0.1700
Data Index: 7851731 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.6075. Min Act: -0.1700
Data Index: 6901238 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.5450. Min Act: -0.1700
Data Index: 4439696 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.5137. Min Act: -0.1700
Data Index: 6853015 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.5137. Min Act: -0.1700
Data Index: 3815948 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.5137. Min Act: -0.1700
Data Index: 967537 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.5137. Min Act: -0.1700
Data Index: 7703748 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.5137. Min Act: -0.1700
Data Index: 3079022 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2637. Min Range: -7.2637
Max Act: 6.4825. Min Act: -0.1700
Data Index: 5699993 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19