Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.1345. Min Act: -0.1700
Data Index: 7798376 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.9156. Min Act: -0.1700
Data Index: 977755 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.9156. Min Act: -0.1700
Data Index: 6501750 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.9156. Min Act: -0.1700
Data Index: 4329900 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8844. Min Act: -0.1700
Data Index: 7138722 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8531. Min Act: -0.1696
Data Index: 3995716 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8531. Min Act: -0.1700
Data Index: 5282999 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8531. Min Act: -0.1700
Data Index: 790493 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8531. Min Act: -0.1695
Data Index: 6315494 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8531. Min Act: -0.1700
Data Index: 8257679 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8218. Min Act: -0.1700
Data Index: 2729387 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8218. Min Act: -0.1700
Data Index: 7885056 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8218. Min Act: -0.1700
Data Index: 4928299 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.7906. Min Act: -0.1700
Data Index: 8237489 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.8218. Min Act: -0.1700
Data Index: 6266128 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.7906. Min Act: -0.1700
Data Index: 1635085 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.7906. Min Act: -0.1700
Data Index: 3101257 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.7906. Min Act: -0.1700
Data Index: 1069728 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.7906. Min Act: -0.1700
Data Index: 5283001 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1345. Min Range: -4.1345
Max Act: 3.7906. Min Act: -0.1700
Data Index: 6438410 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19