Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1252 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.1918. Min Act: -0.1700
Data Index: 8330092 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.1446. Min Act: -0.1700
Data Index: 2474720 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0974. Min Act: -0.1700
Data Index: 4392110 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0974. Min Act: -0.1700
Data Index: 1929626 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0974. Min Act: -0.1700
Data Index: 785091 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0816. Min Act: -0.1700
Data Index: 5866606 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0816. Min Act: -0.1700
Data Index: 2495964 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0658. Min Act: -0.1700
Data Index: 403622 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0658. Min Act: -0.1700
Data Index: 1354779 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0343. Min Act: -0.1700
Data Index: 8320426 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0343. Min Act: -0.1699
Data Index: 2083920 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0343. Min Act: -0.1700
Data Index: 6559678 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0343. Min Act: -0.1700
Data Index: 4242139 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0185. Min Act: -0.1700
Data Index: 5659882 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0185. Min Act: -0.1700
Data Index: 5470133 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0343. Min Act: -0.1700
Data Index: 8032562 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0343. Min Act: -0.1700
Data Index: 3728036 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0185. Min Act: -0.1700
Data Index: 3042001 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0185. Min Act: -0.1700
Data Index: 8432182 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1918. Min Range: -3.1918
Max Act: 3.0185. Min Act: -0.1700
Data Index: 2164638 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19