Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.2287. Min Act: -0.1700
Data Index: 1930539 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.1662. Min Act: -0.1700
Data Index: 1006734 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.1662. Min Act: -0.1700
Data Index: 4549940 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0725. Min Act: -0.1700
Data Index: 4102751 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0725. Min Act: -0.1700
Data Index: 3218354 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0099. Min Act: -0.1700
Data Index: 2207969 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9787. Min Act: -0.1700
Data Index: 7771516 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9787. Min Act: -0.1700
Data Index: 3173830 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9787. Min Act: -0.1700
Data Index: 6234627 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9787. Min Act: -0.1700
Data Index: 4668748 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9162. Min Act: -0.1700
Data Index: 2620316 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9787. Min Act: -0.1700
Data Index: 4551385 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9787. Min Act: -0.1700
Data Index: 8613459 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9787. Min Act: -0.1700
Data Index: 7516061 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 355118 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 5228960 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 2945358 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 2793372 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 6428677 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 3232605 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19