Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2805. Min Range: -5.2805
Max Act: 5.2805. Min Act: -0.1700
Data Index: 8270271 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.9992. Min Act: -0.1700
Data Index: 3238222 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.8430. Min Act: -0.1700
Data Index: 534861 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.7805. Min Act: -0.1700
Data Index: 484153 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.7805. Min Act: -0.1700
Data Index: 693397 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.7492. Min Act: -0.1700
Data Index: 5890579 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.7492. Min Act: -0.1700
Data Index: 1267072 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.7492. Min Act: -0.1700
Data Index: 7705920 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.7492. Min Act: -0.1700
Data Index: 371122 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.7492. Min Act: -0.1700
Data Index: 6931296 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.7180. Min Act: -0.1700
Data Index: 1769641 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6867. Min Act: -0.1700
Data Index: 699732 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6867. Min Act: -0.1700
Data Index: 7309186 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6867. Min Act: -0.1700
Data Index: 890244 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6555. Min Act: -0.1700
Data Index: 3089715 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6555. Min Act: -0.1700
Data Index: 7406670 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6242. Min Act: -0.1700
Data Index: 1655136 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6242. Min Act: -0.1700
Data Index: 4028198 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6242. Min Act: -0.1700
Data Index: 6534592 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2805. Min Range: -5.2805
Max Act: 4.6242. Min Act: -0.1700
Data Index: 6201897 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19