Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4728 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.7412. Min Act: -0.1700
Data Index: 7344016 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.6943. Min Act: -0.1700
Data Index: 5825336 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.6786. Min Act: -0.1700
Data Index: 3849813 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.6786. Min Act: -0.1700
Data Index: 3849811 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.6786. Min Act: -0.1700
Data Index: 210967 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.6474. Min Act: -0.1700
Data Index: 1968718 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.6317. Min Act: -0.1700
Data Index: 4069333 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.6004. Min Act: -0.1700
Data Index: 7344015 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5848. Min Act: -0.1700
Data Index: 3429359 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5848. Min Act: -0.1700
Data Index: 1512305 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.6004. Min Act: -0.1700
Data Index: 3849810 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5848. Min Act: -0.1700
Data Index: 4849045 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5848. Min Act: -0.1700
Data Index: 3717598 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5691. Min Act: -0.1700
Data Index: 8204036 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5378. Min Act: -0.1700
Data Index: 6885027 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5378. Min Act: -0.1700
Data Index: 8612530 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5221. Min Act: -0.1700
Data Index: 3025680 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.5065. Min Act: -0.1700
Data Index: 6599400 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.4751. Min Act: -0.1700
Data Index: 8579560 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7412. Min Range: -3.7412
Max Act: 3.4438. Min Act: -0.1700
Data Index: 4534289 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19