Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1344 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.9432. Min Act: -0.1700
Data Index: 4101475 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.7870. Min Act: -0.1700
Data Index: 986246 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.7557. Min Act: -0.1700
Data Index: 446508 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.7557. Min Act: -0.1700
Data Index: 3805399 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.7557. Min Act: -0.1700
Data Index: 3012145 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.7245. Min Act: -0.1700
Data Index: 2386657 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.7245. Min Act: -0.1700
Data Index: 615584 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6932. Min Act: -0.1700
Data Index: 5164308 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6932. Min Act: -0.1700
Data Index: 3101781 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6932. Min Act: -0.1700
Data Index: 1679570 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6932. Min Act: -0.1700
Data Index: 4246590 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6932. Min Act: -0.1700
Data Index: 3089096 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6932. Min Act: -0.1700
Data Index: 4318513 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6620. Min Act: -0.1700
Data Index: 4342245 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6620. Min Act: -0.1700
Data Index: 3681902 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6620. Min Act: -0.1700
Data Index: 3699365 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6620. Min Act: -0.1700
Data Index: 7603668 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6620. Min Act: -0.1700
Data Index: 4675949 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6620. Min Act: -0.1700
Data Index: 8510399 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9432. Min Range: -4.9432
Max Act: 4.6620. Min Act: -0.1700
Data Index: 4718837 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19