Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0167. Min Range: -5.0167
Max Act: 5.0167. Min Act: -0.1700
Data Index: 4890472 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0167. Min Range: -5.0167
Max Act: 5.0167. Min Act: -0.1700
Data Index: 4890473 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0167. Min Range: -5.0167
Max Act: 5.0167. Min Act: -0.1700
Data Index: 5894289 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0167. Min Range: -5.0167
Max Act: 5.0167. Min Act: -0.1700
Data Index: 7728595 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.9855. Min Act: -0.1700
Data Index: 7419885 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.9542. Min Act: -0.1700
Data Index: 643251 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.9542. Min Act: -0.1700
Data Index: 6498914 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.9230. Min Act: -0.1700
Data Index: 7438104 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.9230. Min Act: -0.1700
Data Index: 5961531 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 2681650 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.9230. Min Act: -0.1700
Data Index: 2270470 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 5569564 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 3985398 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 4323957 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 4528854 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 2100206 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 2588992 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 789445 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 7880185 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0167. Min Range: -5.0167
Max Act: 4.8917. Min Act: -0.1700
Data Index: 5497679 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19