Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.9135. Min Act: -0.1700
Data Index: 2484950 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.7885. Min Act: -0.1700
Data Index: 6304233 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.7885. Min Act: -0.1700
Data Index: 3450370 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.7572. Min Act: -0.1700
Data Index: 3005678 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.7260. Min Act: -0.1700
Data Index: 7682055 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6635. Min Act: -0.1700
Data Index: 6488384 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6322. Min Act: -0.1700
Data Index: 196661 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6322. Min Act: -0.1700
Data Index: 3024629 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6322. Min Act: -0.1700
Data Index: 5985099 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6322. Min Act: -0.1700
Data Index: 4647286 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6322. Min Act: -0.1700
Data Index: 7020985 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6322. Min Act: -0.1700
Data Index: 1628692 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6322. Min Act: -0.1700
Data Index: 7840315 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6010. Min Act: -0.1700
Data Index: 5694540 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6010. Min Act: -0.1700
Data Index: 5727908 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6010. Min Act: -0.1700
Data Index: 7174474 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6010. Min Act: -0.1700
Data Index: 1536492 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.6010. Min Act: -0.1700
Data Index: 1490333 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.5697. Min Act: -0.1700
Data Index: 1536493 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9135. Min Range: -5.9135
Max Act: 5.5697. Min Act: -0.1700
Data Index: 5434783 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19