Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2397 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.8522. Min Act: -0.1700
Data Index: 3049163 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.4766. Min Act: -0.1700
Data Index: 2014501 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.4610. Min Act: -0.1700
Data Index: 3984022 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.4140. Min Act: -0.1700
Data Index: 2910422 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.4140. Min Act: -0.1700
Data Index: 4205484 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3983. Min Act: -0.1700
Data Index: 4845238 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3826. Min Act: -0.1700
Data Index: 2362190 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3826. Min Act: -0.1700
Data Index: 723199 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3669. Min Act: -0.1700
Data Index: 3460133 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3983. Min Act: -0.1700
Data Index: 2248940 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3826. Min Act: -0.1700
Data Index: 2868343 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3512. Min Act: -0.1700
Data Index: 1288410 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3512. Min Act: -0.1700
Data Index: 6659746 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3669. Min Act: -0.1700
Data Index: 8410572 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3669. Min Act: -0.1700
Data Index: 2364731 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3512. Min Act: -0.1700
Data Index: 2383840 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3512. Min Act: -0.1700
Data Index: 5503432 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3355. Min Act: -0.1700
Data Index: 2810838 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3355. Min Act: -0.1700
Data Index: 4825309 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8522. Min Range: -3.8522
Max Act: 3.3355. Min Act: -0.1700
Data Index: 1639086 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19