Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1930 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2672. Min Range: -5.2672
Max Act: 5.2672. Min Act: -0.1700
Data Index: 5834124 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2672. Min Range: -5.2672
Max Act: 5.1422. Min Act: -0.1700
Data Index: 1791183 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2672. Min Range: -5.2672
Max Act: 5.1422. Min Act: -0.1700
Data Index: 7509016 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2672. Min Range: -5.2672
Max Act: 5.0172. Min Act: -0.1700
Data Index: 3825581 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9859. Min Act: -0.1700
Data Index: 8678924 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9547. Min Act: -0.1700
Data Index: 5434583 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2672. Min Range: -5.2672
Max Act: 5.0172. Min Act: -0.1700
Data Index: 8495998 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9547. Min Act: -0.1700
Data Index: 2832506 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9859. Min Act: -0.1700
Data Index: 5933652 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9859. Min Act: -0.1700
Data Index: 7928865 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2672. Min Range: -5.2672
Max Act: 5.0172. Min Act: -0.1700
Data Index: 7219620 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.8922. Min Act: -0.1700
Data Index: 5149896 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9547. Min Act: -0.1700
Data Index: 8437528 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9234. Min Act: -0.1700
Data Index: 3315636 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9547. Min Act: -0.1700
Data Index: 1454918 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9234. Min Act: -0.1700
Data Index: 6424065 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9234. Min Act: -0.1700
Data Index: 8741226 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.9234. Min Act: -0.1700
Data Index: 826355 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.8922. Min Act: -0.1700
Data Index: 430194 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2672. Min Range: -5.2672
Max Act: 4.8609. Min Act: -0.1700
Data Index: 2268412 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19