Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0302. Min Range: -6.0302
Max Act: 6.0302. Min Act: -0.1700
Data Index: 7532328 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.9677. Min Act: -0.1700
Data Index: 7529613 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.9364. Min Act: -0.1700
Data Index: 8824130 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.8739. Min Act: -0.1700
Data Index: 2810242 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.9052. Min Act: -0.1700
Data Index: 3091216 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.8114. Min Act: -0.1700
Data Index: 1541150 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.8427. Min Act: -0.1700
Data Index: 3082556 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.8427. Min Act: -0.1700
Data Index: 1915455 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.7802. Min Act: -0.1700
Data Index: 6451617 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.7802. Min Act: -0.1700
Data Index: 3523550 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.7489. Min Act: -0.1700
Data Index: 1462550 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.7489. Min Act: -0.1700
Data Index: 712029 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.7489. Min Act: -0.1700
Data Index: 6608338 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.7489. Min Act: -0.1700
Data Index: 2353938 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.7177. Min Act: -0.1700
Data Index: 6078402 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.7177. Min Act: -0.1700
Data Index: 2239446 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.6864. Min Act: -0.1700
Data Index: 712025 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.6864. Min Act: -0.1700
Data Index: 6204593 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.6864. Min Act: -0.1700
Data Index: 6108398 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0302. Min Range: -6.0302
Max Act: 5.6864. Min Act: -0.1700
Data Index: 6918107 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19