Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3996 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5643. Min Range: -7.5643
Max Act: 7.5643. Min Act: -0.1700
Data Index: 1296989 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5643. Min Range: -7.5643
Max Act: 7.3143. Min Act: -0.1700
Data Index: 1436697 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5643. Min Range: -7.5643
Max Act: 7.0643. Min Act: -0.1700
Data Index: 5236183 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5643. Min Range: -7.5643
Max Act: 7.0330. Min Act: -0.1700
Data Index: 7636214 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5643. Min Range: -7.5643
Max Act: 7.0330. Min Act: -0.1700
Data Index: 4018670 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5643. Min Range: -7.5643
Max Act: 7.0018. Min Act: -0.1700
Data Index: 6243147 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5643. Min Range: -7.5643
Max Act: 7.0018. Min Act: -0.1700
Data Index: 3473839 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5643. Min Range: -7.5643
Max Act: 7.0018. Min Act: -0.1700
Data Index: 7920314 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.9705. Min Act: -0.1700
Data Index: 1986292 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.9705. Min Act: -0.1700
Data Index: 8195429 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.9705. Min Act: -0.1700
Data Index: 1711357 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.9705. Min Act: -0.1700
Data Index: 3186622 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.8768. Min Act: -0.1700
Data Index: 4624189 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.8768. Min Act: -0.1700
Data Index: 2126795 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.8455. Min Act: -0.1700
Data Index: 2274035 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.8455. Min Act: -0.1700
Data Index: 1126814 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.8455. Min Act: -0.1700
Data Index: 5370577 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.8455. Min Act: -0.1700
Data Index: 4327187 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.8143. Min Act: -0.1700
Data Index: 1828979 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5643. Min Range: -7.5643
Max Act: 6.8143. Min Act: -0.1700
Data Index: 3036677 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19