Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.2172. Min Act: -0.1700
Data Index: 6107864 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.2172. Min Act: -0.1700
Data Index: 6869606 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.1859. Min Act: -0.1700
Data Index: 4961013 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.1859. Min Act: -0.1700
Data Index: 4149001 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.1547. Min Act: -0.1700
Data Index: 6523241 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.1234. Min Act: -0.1700
Data Index: 453041 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.1547. Min Act: -0.1700
Data Index: 5908066 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.1234. Min Act: -0.1700
Data Index: 3423307 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.1234. Min Act: -0.1700
Data Index: 4873477 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0609. Min Act: -0.1700
Data Index: 7979561 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0609. Min Act: -0.1700
Data Index: 1619651 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0609. Min Act: -0.1700
Data Index: 4873476 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0609. Min Act: -0.1700
Data Index: 8319547 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0297. Min Act: -0.1700
Data Index: 4562897 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0297. Min Act: -0.1700
Data Index: 7504721 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0297. Min Act: -0.1700
Data Index: 7880953 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0297. Min Act: -0.1700
Data Index: 6407467 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0297. Min Act: -0.1698
Data Index: 2788192 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2172. Min Range: -5.2172
Max Act: 5.0297. Min Act: -0.1700
Data Index: 4375607 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2172. Min Range: -5.2172
Max Act: 4.9984. Min Act: -0.1700
Data Index: 7578456 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19