Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.2537. Min Act: -0.1700
Data Index: 1847310 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.1287. Min Act: -0.1700
Data Index: 8150483 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0974. Min Act: -0.1700
Data Index: 6425325 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.1599. Min Act: -0.1700
Data Index: 8799240 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.1287. Min Act: -0.1700
Data Index: 8755661 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.1599. Min Act: -0.1700
Data Index: 3436892 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0974. Min Act: -0.1700
Data Index: 7181089 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0974. Min Act: -0.1700
Data Index: 8308199 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0662. Min Act: -0.1700
Data Index: 7659355 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0662. Min Act: -0.1700
Data Index: 510562 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0349. Min Act: -0.1700
Data Index: 565830 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0662. Min Act: -0.1700
Data Index: 6324006 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0349. Min Act: -0.1700
Data Index: 2391438 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2537. Min Range: -6.2537
Max Act: 6.0037. Min Act: -0.1700
Data Index: 1411271 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2537. Min Range: -6.2537
Max Act: 5.9724. Min Act: -0.1700
Data Index: 7209014 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2537. Min Range: -6.2537
Max Act: 5.9724. Min Act: -0.1700
Data Index: 6602507 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2537. Min Range: -6.2537
Max Act: 5.9412. Min Act: -0.1700
Data Index: 8195175 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2537. Min Range: -6.2537
Max Act: 5.9099. Min Act: -0.1700
Data Index: 2349232 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2537. Min Range: -6.2537
Max Act: 5.9412. Min Act: -0.1700
Data Index: 7324775 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2537. Min Range: -6.2537
Max Act: 5.9412. Min Act: -0.1700
Data Index: 5195315 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19