Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.4452. Min Act: -0.1700
Data Index: 1421835 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.4140. Min Act: -0.1700
Data Index: 464731 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.4452. Min Act: -0.1700
Data Index: 492967 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.3827. Min Act: -0.1700
Data Index: 4204433 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.3827. Min Act: -0.1700
Data Index: 2115700 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2890. Min Act: -0.1700
Data Index: 4460625 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.3202. Min Act: -0.1700
Data Index: 8456920 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.3202. Min Act: -0.1700
Data Index: 6780094 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2890. Min Act: -0.1700
Data Index: 3280282 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2577. Min Act: -0.1700
Data Index: 6625121 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2890. Min Act: -0.1700
Data Index: 2115697 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2890. Min Act: -0.1700
Data Index: 2272103 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2577. Min Act: -0.1700
Data Index: 2272104 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2264. Min Act: -0.1700
Data Index: 8389415 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2264. Min Act: -0.1700
Data Index: 5088825 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.2264. Min Act: -0.1700
Data Index: 2191830 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.1952. Min Act: -0.1700
Data Index: 3385153 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.1952. Min Act: -0.1700
Data Index: 612493 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.1952. Min Act: -0.1700
Data Index: 4204437 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4452. Min Range: -4.4452
Max Act: 4.1952. Min Act: -0.1700
Data Index: 1136385 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19