Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4638 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2471. Min Range: -5.2471
Max Act: 5.2471. Min Act: -0.1700
Data Index: 8631698 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.8408. Min Act: -0.1700
Data Index: 18857 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.8096. Min Act: -0.1700
Data Index: 4222383 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.7783. Min Act: -0.1700
Data Index: 88993 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.7783. Min Act: -0.1700
Data Index: 1944056 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.7471. Min Act: -0.1700
Data Index: 2719140 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6846. Min Act: -0.1700
Data Index: 4887643 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6846. Min Act: -0.1700
Data Index: 1825658 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6846. Min Act: -0.1700
Data Index: 2614069 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6846. Min Act: -0.1700
Data Index: 1548054 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6533. Min Act: -0.1700
Data Index: 6732901 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6846. Min Act: -0.1700
Data Index: 7022209 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6533. Min Act: -0.1700
Data Index: 3259565 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6533. Min Act: -0.1700
Data Index: 4553776 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6533. Min Act: -0.1700
Data Index: 5278143 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6533. Min Act: -0.1700
Data Index: 164827 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6221. Min Act: -0.1700
Data Index: 5856334 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6221. Min Act: -0.1700
Data Index: 721714 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6221. Min Act: -0.1700
Data Index: 4253748 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2471. Min Range: -5.2471
Max Act: 4.6221. Min Act: -0.1700
Data Index: 1795337 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19