Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.6030. Min Act: -0.1700
Data Index: 1956759 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.6030. Min Act: -0.1700
Data Index: 1469776 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.5717. Min Act: -0.1700
Data Index: 8339683 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.5248. Min Act: -0.1700
Data Index: 3947332 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.5091. Min Act: -0.1700
Data Index: 6085049 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4621. Min Act: -0.1700
Data Index: 5615698 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4621. Min Act: -0.1700
Data Index: 89887 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4621. Min Act: -0.1700
Data Index: 142917 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4621. Min Act: -0.1700
Data Index: 2860248 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4621. Min Act: -0.1700
Data Index: 3160996 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4308. Min Act: -0.1700
Data Index: 6083004 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4151. Min Act: -0.1700
Data Index: 5478634 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4151. Min Act: -0.1700
Data Index: 1076219 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.4308. Min Act: -0.1700
Data Index: 131644 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.3994. Min Act: -0.1700
Data Index: 4983420 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.3837. Min Act: -0.1700
Data Index: 41619 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.3837. Min Act: -0.1700
Data Index: 8280224 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.3681. Min Act: -0.1700
Data Index: 349436 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.3524. Min Act: -0.1700
Data Index: 6438089 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6030. Min Range: -3.6030
Max Act: 3.3524. Min Act: -0.1700
Data Index: 8280221 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19