Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1295. Min Range: -6.1295
Max Act: 6.1295. Min Act: -0.1700
Data Index: 5713321 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1295. Min Range: -6.1295
Max Act: 6.0045. Min Act: -0.1700
Data Index: 3746775 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.9733. Min Act: -0.1700
Data Index: 3193512 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.8483. Min Act: -0.1700
Data Index: 222272 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.8170. Min Act: -0.1700
Data Index: 2502532 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.8170. Min Act: -0.1700
Data Index: 795760 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.7858. Min Act: -0.1700
Data Index: 2698308 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.8170. Min Act: -0.1700
Data Index: 25116 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.7545. Min Act: -0.1700
Data Index: 4857885 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.7233. Min Act: -0.1700
Data Index: 7918660 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.6920. Min Act: -0.1700
Data Index: 3028784 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.7233. Min Act: -0.1700
Data Index: 8402007 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.7233. Min Act: -0.1700
Data Index: 7663359 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.7233. Min Act: -0.1700
Data Index: 5664854 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.6920. Min Act: -0.1700
Data Index: 2617043 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.6920. Min Act: -0.1700
Data Index: 478976 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.6920. Min Act: -0.1700
Data Index: 1149630 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.6608. Min Act: -0.1700
Data Index: 1281027 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.6295. Min Act: -0.1700
Data Index: 3144183 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1295. Min Range: -6.1295
Max Act: 5.6295. Min Act: -0.1700
Data Index: 7050769 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19