Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2167 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.9634. Min Act: -0.1700
Data Index: 3807765 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.9159. Min Act: -0.1700
Data Index: 5283877 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.8683. Min Act: -0.1700
Data Index: 4811258 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.8683. Min Act: -0.1700
Data Index: 2105150 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.8206. Min Act: -0.1700
Data Index: 4367214 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.8365. Min Act: -0.1700
Data Index: 5236935 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.8206. Min Act: -0.1700
Data Index: 4955199 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7888. Min Act: -0.1700
Data Index: 2908709 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.8047. Min Act: -0.1700
Data Index: 2815253 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.8047. Min Act: -0.1700
Data Index: 2683639 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7569. Min Act: -0.1700
Data Index: 8699845 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7728. Min Act: -0.1700
Data Index: 6614887 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7728. Min Act: -0.1700
Data Index: 3649483 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7728. Min Act: -0.1700
Data Index: 7934270 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7409. Min Act: -0.1700
Data Index: 250847 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7409. Min Act: -0.1700
Data Index: 7367235 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7569. Min Act: -0.1700
Data Index: 4093815 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7409. Min Act: -0.1700
Data Index: 7168026 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7728. Min Act: -0.1700
Data Index: 7840379 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9634. Min Range: -2.9634
Max Act: 2.7569. Min Act: -0.1700
Data Index: 7491745 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19