Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.8683. Min Act: -0.1700
Data Index: 5043137 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.8370. Min Act: -0.1700
Data Index: 5043128 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.7275. Min Act: -0.1700
Data Index: 5043134 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.6806. Min Act: -0.1700
Data Index: 209083 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.6180. Min Act: -0.1700
Data Index: 2295145 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.5711. Min Act: -0.1700
Data Index: 7320300 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.5554. Min Act: -0.1700
Data Index: 7361313 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.5397. Min Act: -0.1700
Data Index: 4919632 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.5084. Min Act: -0.1700
Data Index: 6044936 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.5241. Min Act: -0.1700
Data Index: 4013887 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.5084. Min Act: -0.1700
Data Index: 418402 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.4928. Min Act: -0.1700
Data Index: 3561391 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.4771. Min Act: -0.1700
Data Index: 8035977 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.4928. Min Act: -0.1700
Data Index: 1265637 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.5084. Min Act: -0.1700
Data Index: 5043138 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.4928. Min Act: -0.1700
Data Index: 3162104 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.4614. Min Act: -0.1700
Data Index: 3861979 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.4458. Min Act: -0.1700
Data Index: 2805497 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.4614. Min Act: -0.1700
Data Index: 5265903 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8683. Min Range: -3.8683
Max Act: 3.4771. Min Act: -0.1700
Data Index: 1992850 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19