Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1411 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.8099. Min Act: -0.1700
Data Index: 2581180 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.5909. Min Act: -0.1700
Data Index: 366076 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.5282. Min Act: -0.1700
Data Index: 225361 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.5126. Min Act: -0.1700
Data Index: 1138657 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.4656. Min Act: -0.1700
Data Index: 8654365 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.4343. Min Act: -0.1700
Data Index: 6038571 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.4029. Min Act: -0.1700
Data Index: 543246 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.4186. Min Act: -0.1700
Data Index: 5710151 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.4029. Min Act: -0.1700
Data Index: 7982320 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.3715. Min Act: -0.1700
Data Index: 2561586 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.3715. Min Act: -0.1700
Data Index: 8384186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.3715. Min Act: -0.1700
Data Index: 180938 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.3402. Min Act: -0.1700
Data Index: 1938137 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.3402. Min Act: -0.1700
Data Index: 3916994 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.3245. Min Act: -0.1700
Data Index: 7117154 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.3088. Min Act: -0.1700
Data Index: 6669975 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.2931. Min Act: -0.1700
Data Index: 1539350 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.2774. Min Act: -0.1700
Data Index: 4279164 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.2617. Min Act: -0.1700
Data Index: 7876926 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8099. Min Range: -3.8099
Max Act: 3.2460. Min Act: -0.1700
Data Index: 7691184 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19