Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2754. Min Act: -0.1700
Data Index: 3676629 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2754. Min Act: -0.1700
Data Index: 7120507 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2754. Min Act: -0.1700
Data Index: 5775090 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2754. Min Act: -0.1700
Data Index: 4245278 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 8357990 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2442. Min Act: -0.1700
Data Index: 2625699 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2442. Min Act: -0.1700
Data Index: 8146338 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 2718477 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 6825397 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2442. Min Act: -0.1700
Data Index: 1588561 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 7579444 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 7409512 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2129. Min Act: -0.1696
Data Index: 3987317 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 8431312 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.2129. Min Act: -0.1700
Data Index: 967770 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.1817. Min Act: -0.1700
Data Index: 5379299 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.1817. Min Act: -0.1700
Data Index: 1084443 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.1817. Min Act: -0.1700
Data Index: 7148919 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.1817. Min Act: -0.1700
Data Index: 6554826 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2754. Min Range: -5.2754
Max Act: 5.1817. Min Act: -0.1700
Data Index: 1206173 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19