Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.5263. Min Act: -0.1700
Data Index: 1902873 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.3700. Min Act: -0.1700
Data Index: 1556752 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.3700. Min Act: -0.1700
Data Index: 6034571 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.3387. Min Act: -0.1700
Data Index: 7372055 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.3700. Min Act: -0.1700
Data Index: 8245983 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2762. Min Act: -0.1700
Data Index: 769607 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.3075. Min Act: -0.1700
Data Index: 7810967 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2762. Min Act: -0.1700
Data Index: 2101487 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2762. Min Act: -0.1700
Data Index: 8157558 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2762. Min Act: -0.1700
Data Index: 3893201 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2450. Min Act: -0.1700
Data Index: 101190 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2762. Min Act: -0.1700
Data Index: 1484385 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2137. Min Act: -0.1700
Data Index: 905403 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2137. Min Act: -0.1700
Data Index: 4361823 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2450. Min Act: -0.1700
Data Index: 151280 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2450. Min Act: -0.1700
Data Index: 6378991 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.1825. Min Act: -0.1700
Data Index: 6075249 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2137. Min Act: -0.1700
Data Index: 2629069 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2137. Min Act: -0.1700
Data Index: 2085456 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5263. Min Range: -4.5263
Max Act: 4.2137. Min Act: -0.1700
Data Index: 3382066 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19