Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1532 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0720. Min Range: -2.0720
Max Act: 2.0720. Min Act: -0.1700
Data Index: 3137757 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.9284. Min Act: -0.1700
Data Index: 6271455 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8943. Min Act: -0.1700
Data Index: 3378546 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8943. Min Act: -0.1700
Data Index: 8234336 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.9114. Min Act: -0.1700
Data Index: 8518402 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8858. Min Act: -0.1700
Data Index: 2650278 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8858. Min Act: -0.1700
Data Index: 7245091 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8858. Min Act: -0.1700
Data Index: 3448248 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8772. Min Act: -0.1700
Data Index: 3962767 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8772. Min Act: -0.1700
Data Index: 944164 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8687. Min Act: -0.1700
Data Index: 1102262 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8772. Min Act: -0.1700
Data Index: 7738387 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8601. Min Act: -0.1700
Data Index: 5420675 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8430. Min Act: -0.1700
Data Index: 4561226 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8516. Min Act: -0.1700
Data Index: 1913862 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8601. Min Act: -0.1700
Data Index: 7164626 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8601. Min Act: -0.1700
Data Index: 526380 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8430. Min Act: -0.1700
Data Index: 914268 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8516. Min Act: -0.1700
Data Index: 1230523 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0720. Min Range: -2.0720
Max Act: 1.8516. Min Act: -0.1700
Data Index: 8000596 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19