Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4808. Min Act: -0.1700
Data Index: 1513661 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4495. Min Act: -0.1700
Data Index: 4034927 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.3870. Min Act: -0.1700
Data Index: 8674126 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 829220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 759341 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 8605553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 7967115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 7534619 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 6248431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 368263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 6114795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 217479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 5805241 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 4230188 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 173763 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 3483101 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 3033245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 2514934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 2297436 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4808. Min Range: -5.4808
Max Act: 5.4183. Min Act: -0.1700
Data Index: 879950 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19