Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.8902. Min Act: -0.1700
Data Index: 5434839 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.9215. Min Act: -0.1700
Data Index: 4215835 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.8902. Min Act: -0.1700
Data Index: 4049045 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.8902. Min Act: -0.1700
Data Index: 3705785 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7964. Min Act: -0.1700
Data Index: 2077335 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7964. Min Act: -0.1700
Data Index: 2587042 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7964. Min Act: -0.1700
Data Index: 5098463 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7651. Min Act: -0.1700
Data Index: 356608 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7339. Min Act: -0.1700
Data Index: 6893574 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7339. Min Act: -0.1700
Data Index: 532225 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7339. Min Act: -0.1700
Data Index: 808385 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7339. Min Act: -0.1700
Data Index: 1917005 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7339. Min Act: -0.1700
Data Index: 4931217 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7651. Min Act: -0.1700
Data Index: 2999036 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7339. Min Act: -0.1700
Data Index: 2471516 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7651. Min Act: -0.1700
Data Index: 1278223 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7026. Min Act: -0.1700
Data Index: 5607122 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7026. Min Act: -0.1700
Data Index: 810122 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7026. Min Act: -0.1700
Data Index: 1260275 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9215. Min Range: -3.9215
Max Act: 3.7651. Min Act: -0.1700
Data Index: 275206 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19