Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0143. Min Range: -7.0143
Max Act: 7.0143. Min Act: -0.1700
Data Index: 5823030 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.7018. Min Act: -0.1700
Data Index: 4304180 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.4831. Min Act: -0.1700
Data Index: 8501297 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.4518. Min Act: -0.1700
Data Index: 6578036 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.3893. Min Act: -0.1700
Data Index: 1840684 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.3893. Min Act: -0.1700
Data Index: 4443526 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.3893. Min Act: -0.1700
Data Index: 3606850 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.3268. Min Act: -0.1700
Data Index: 690166 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.3268. Min Act: -0.1700
Data Index: 5291055 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.2331. Min Act: -0.1700
Data Index: 3295542 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.1393. Min Act: -0.1700
Data Index: 3049715 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.1393. Min Act: -0.1700
Data Index: 1940347 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.1393. Min Act: -0.1700
Data Index: 6458970 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.1393. Min Act: -0.1700
Data Index: 7281786 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.1081. Min Act: -0.1700
Data Index: 2728733 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.0768. Min Act: -0.1700
Data Index: 2266978 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.0768. Min Act: -0.1700
Data Index: 198254 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.0768. Min Act: -0.1700
Data Index: 6107794 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.0143. Min Act: -0.1700
Data Index: 7067547 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0143. Min Range: -7.0143
Max Act: 6.0456. Min Act: -0.1700
Data Index: 8216222 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19