Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.8568. Min Act: -0.1700
Data Index: 4733653 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.5131. Min Act: -0.1700
Data Index: 1183021 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.4506. Min Act: -0.1700
Data Index: 7421459 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.4506. Min Act: -0.1700
Data Index: 3125372 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.4506. Min Act: -0.1700
Data Index: 6802839 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.4506. Min Act: -0.1700
Data Index: 1886727 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.3568. Min Act: -0.1700
Data Index: 5164660 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.3256. Min Act: -0.1700
Data Index: 2006477 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.3256. Min Act: -0.1700
Data Index: 7320001 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.2943. Min Act: -0.1700
Data Index: 101260 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.2943. Min Act: -0.1700
Data Index: 7339866 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.2006. Min Act: -0.1700
Data Index: 748055 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.2318. Min Act: -0.1700
Data Index: 8788139 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.2006. Min Act: -0.1700
Data Index: 7643187 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.1693. Min Act: -0.1700
Data Index: 458633 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.2006. Min Act: -0.1700
Data Index: 3676962 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.2006. Min Act: -0.1700
Data Index: 8728729 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.2006. Min Act: -0.1700
Data Index: 4481142 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.1693. Min Act: -0.1700
Data Index: 1367996 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8568. Min Range: -6.8568
Max Act: 6.1693. Min Act: -0.1700
Data Index: 3854210 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19