Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2250. Min Range: -5.2250
Max Act: 5.2250. Min Act: -0.1700
Data Index: 3186186 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2250. Min Range: -5.2250
Max Act: 5.0687. Min Act: -0.1700
Data Index: 3697903 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2250. Min Range: -5.2250
Max Act: 5.0375. Min Act: -0.1700
Data Index: 5714390 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2250. Min Range: -5.2250
Max Act: 5.0375. Min Act: -0.1700
Data Index: 3544186 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2250. Min Range: -5.2250
Max Act: 5.0062. Min Act: -0.1700
Data Index: 7123882 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2250. Min Range: -5.2250
Max Act: 5.0062. Min Act: -0.1700
Data Index: 7732818 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2250. Min Range: -5.2250
Max Act: 5.0062. Min Act: -0.1700
Data Index: 8401670 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9750. Min Act: -0.1700
Data Index: 396218 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9750. Min Act: -0.1700
Data Index: 2888611 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9437. Min Act: -0.1700
Data Index: 2302918 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9750. Min Act: -0.1700
Data Index: 4587155 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9437. Min Act: -0.1700
Data Index: 8186920 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9437. Min Act: -0.1700
Data Index: 4066708 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9750. Min Act: -0.1700
Data Index: 146490 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9750. Min Act: -0.1700
Data Index: 5075647 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9437. Min Act: -0.1700
Data Index: 3218411 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9437. Min Act: -0.1700
Data Index: 7414638 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9437. Min Act: -0.1700
Data Index: 2404434 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9125. Min Act: -0.1700
Data Index: 3578657 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2250. Min Range: -5.2250
Max Act: 4.9125. Min Act: -0.1700
Data Index: 3650171 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19