Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.6516. Min Act: -0.1700
Data Index: 4036875 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.5266. Min Act: -0.1700
Data Index: 4633397 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.4328. Min Act: -0.1700
Data Index: 7321006 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.3703. Min Act: -0.1700
Data Index: 2929616 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.3703. Min Act: -0.1700
Data Index: 1008743 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.3391. Min Act: -0.1700
Data Index: 6915337 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.3391. Min Act: -0.1700
Data Index: 4162549 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.3391. Min Act: -0.1700
Data Index: 6880756 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.3078. Min Act: -0.1700
Data Index: 1082075 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2766. Min Act: -0.1700
Data Index: 3812214 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2766. Min Act: -0.1700
Data Index: 4278643 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2766. Min Act: -0.1700
Data Index: 6095748 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2766. Min Act: -0.1700
Data Index: 5390580 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2766. Min Act: -0.1700
Data Index: 6304239 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2766. Min Act: -0.1700
Data Index: 5171455 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2453. Min Act: -0.1700
Data Index: 6946973 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2141. Min Act: -0.1700
Data Index: 1348348 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2141. Min Act: -0.1700
Data Index: 4548657 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.2141. Min Act: -0.1700
Data Index: 8653577 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6516. Min Range: -5.6516
Max Act: 5.1828. Min Act: -0.1700
Data Index: 3693784 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19