Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4774. Min Range: -9.4774
Max Act: 9.4774. Min Act: -0.1700
Data Index: 4133656 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4774. Min Range: -9.4774
Max Act: 9.1024. Min Act: -0.1700
Data Index: 6949399 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4774. Min Range: -9.4774
Max Act: 9.1024. Min Act: -0.1700
Data Index: 4448015 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4774. Min Range: -9.4774
Max Act: 9.0399. Min Act: -0.1700
Data Index: 6744107 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.8524. Min Act: -0.1700
Data Index: 5481984 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.9149. Min Act: -0.1700
Data Index: 2785020 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.9149. Min Act: -0.1700
Data Index: 3450046 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.9149. Min Act: -0.1700
Data Index: 7173003 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.9149. Min Act: -0.1699
Data Index: 635179 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.8524. Min Act: -0.1700
Data Index: 4200774 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.8524. Min Act: -0.1700
Data Index: 3223718 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.8524. Min Act: -0.1700
Data Index: 5290529 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.7274. Min Act: -0.1700
Data Index: 185116 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.6649. Min Act: -0.1700
Data Index: 1662874 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.7274. Min Act: -0.1700
Data Index: 5978306 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.7274. Min Act: -0.1700
Data Index: 1541994 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.7274. Min Act: -0.1700
Data Index: 5028771 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.7274. Min Act: -0.1700
Data Index: 2187904 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.7274. Min Act: -0.1700
Data Index: 3903264 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4774. Min Range: -9.4774
Max Act: 8.7899. Min Act: -0.1700
Data Index: 3855151 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19