Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3292 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0117. Min Range: -4.0117
Max Act: 4.0117. Min Act: -0.1700
Data Index: 3101111 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.9492. Min Act: -0.1700
Data Index: 2876965 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.9179. Min Act: -0.1700
Data Index: 6954981 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8554. Min Act: -0.1700
Data Index: 6372312 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8554. Min Act: -0.1700
Data Index: 5170098 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8554. Min Act: -0.1700
Data Index: 5677398 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8554. Min Act: -0.1700
Data Index: 8397155 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8867. Min Act: -0.1700
Data Index: 7945339 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.8241. Min Act: -0.1700
Data Index: 5093326 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7616. Min Act: -0.1700
Data Index: 8704862 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7616. Min Act: -0.1700
Data Index: 754045 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7616. Min Act: -0.1700
Data Index: 8501332 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7616. Min Act: -0.1700
Data Index: 8728767 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7616. Min Act: -0.1700
Data Index: 4625987 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7616. Min Act: -0.1700
Data Index: 5328057 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7303. Min Act: -0.1700
Data Index: 3175742 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7616. Min Act: -0.1700
Data Index: 1461810 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7303. Min Act: -0.1700
Data Index: 3258270 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7303. Min Act: -0.1700
Data Index: 2633022 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0117. Min Range: -4.0117
Max Act: 3.7303. Min Act: -0.1700
Data Index: 5985887 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19