Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 189 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0479. Min Range: -2.0479
Max Act: 2.0479. Min Act: -0.1700
Data Index: 7791081 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0479. Min Range: -2.0479
Max Act: 2.0479. Min Act: -0.1700
Data Index: 5964672 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9804. Min Act: -0.1700
Data Index: 1569482 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9465. Min Act: -0.1700
Data Index: 6288092 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9465. Min Act: -0.1700
Data Index: 7723948 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9635. Min Act: -0.1700
Data Index: 8134371 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9465. Min Act: -0.1700
Data Index: 1999960 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9295. Min Act: -0.1700
Data Index: 6145309 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9295. Min Act: -0.1700
Data Index: 6519701 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9295. Min Act: -0.1700
Data Index: 5361543 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9125. Min Act: -0.1700
Data Index: 7569245 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.9125. Min Act: -0.1700
Data Index: 1240852 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.8954. Min Act: -0.1700
Data Index: 3971121 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.8784. Min Act: -0.1700
Data Index: 4957292 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.8784. Min Act: -0.1686
Data Index: 2956323 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.8954. Min Act: -0.1700
Data Index: 5119039 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.8784. Min Act: -0.1700
Data Index: 4264920 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.8784. Min Act: -0.1700
Data Index: 1787092 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.8784. Min Act: -0.1700
Data Index: 7341326 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0479. Min Range: -2.0479
Max Act: 1.8784. Min Act: -0.1700
Data Index: 3429788 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19