Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.7849. Min Act: -0.1700
Data Index: 1095974 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.5349. Min Act: -0.1700
Data Index: 5817392 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.4099. Min Act: -0.1700
Data Index: 4072559 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.2849. Min Act: -0.1700
Data Index: 3496780 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.3474. Min Act: -0.1700
Data Index: 5153807 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.2849. Min Act: -0.1700
Data Index: 2484732 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.1599. Min Act: -0.1700
Data Index: 3061919 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.1599. Min Act: -0.1700
Data Index: 3627811 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.1599. Min Act: -0.1700
Data Index: 174470 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.1599. Min Act: -0.1700
Data Index: 4216327 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.0974. Min Act: -0.1700
Data Index: 1906595 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.0974. Min Act: -0.1700
Data Index: 6956454 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7849. Min Range: -8.7849
Max Act: 8.0349. Min Act: -0.1700
Data Index: 3433497 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7849. Min Range: -8.7849
Max Act: 7.9724. Min Act: -0.1700
Data Index: 2220807 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7849. Min Range: -8.7849
Max Act: 7.9724. Min Act: -0.1700
Data Index: 6242252 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7849. Min Range: -8.7849
Max Act: 7.9724. Min Act: -0.1700
Data Index: 1178394 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7849. Min Range: -8.7849
Max Act: 7.9099. Min Act: -0.1700
Data Index: 3177355 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7849. Min Range: -8.7849
Max Act: 7.9724. Min Act: -0.1700
Data Index: 6846315 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7849. Min Range: -8.7849
Max Act: 7.9099. Min Act: -0.1700
Data Index: 6444946 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7849. Min Range: -8.7849
Max Act: 7.8474. Min Act: -0.1700
Data Index: 3918216 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19