Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4209 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.8197. Min Act: -0.1700
Data Index: 4106536 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.7572. Min Act: -0.1699
Data Index: 7491424 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6634. Min Act: -0.1700
Data Index: 2137424 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6947. Min Act: -0.1700
Data Index: 1153939 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6634. Min Act: -0.1700
Data Index: 683495 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6634. Min Act: -0.1698
Data Index: 7415523 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6634. Min Act: -0.1698
Data Index: 5492203 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6322. Min Act: -0.1699
Data Index: 8465881 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6322. Min Act: -0.1700
Data Index: 6155578 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6322. Min Act: -0.1687
Data Index: 7340749 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6009. Min Act: -0.1700
Data Index: 7704952 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6009. Min Act: -0.1700
Data Index: 5316374 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6009. Min Act: -0.1699
Data Index: 7106677 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6009. Min Act: -0.1700
Data Index: 7060229 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.6009. Min Act: -0.1699
Data Index: 1221553 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.5697. Min Act: -0.1700
Data Index: 4629292 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.5697. Min Act: -0.1698
Data Index: 6178723 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.5697. Min Act: -0.1700
Data Index: 332218 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.5697. Min Act: -0.1700
Data Index: 5796878 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8197. Min Range: -4.8197
Max Act: 4.5384. Min Act: -0.1700
Data Index: 5549861 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19