Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5434 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.7150. Min Act: -0.1700
Data Index: 1595424 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.7150. Min Act: -0.1700
Data Index: 7433200 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.5588. Min Act: -0.1700
Data Index: 7561975 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.5275. Min Act: -0.1700
Data Index: 2645290 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4963. Min Act: -0.1700
Data Index: 2302454 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4650. Min Act: -0.1700
Data Index: 1757552 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4650. Min Act: -0.1700
Data Index: 6527412 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4650. Min Act: -0.1700
Data Index: 8270581 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4338. Min Act: -0.1700
Data Index: 5198951 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4650. Min Act: -0.1699
Data Index: 8118072 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4338. Min Act: -0.1700
Data Index: 875215 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4338. Min Act: -0.1700
Data Index: 6746756 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4338. Min Act: -0.1700
Data Index: 1251768 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4338. Min Act: -0.1700
Data Index: 8760779 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4338. Min Act: -0.1700
Data Index: 4564687 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4338. Min Act: -0.1700
Data Index: 7888608 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4025. Min Act: -0.1700
Data Index: 3003655 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.3713. Min Act: -0.1700
Data Index: 2261420 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4025. Min Act: -0.1700
Data Index: 5088794 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7150. Min Range: -5.7150
Max Act: 5.4025. Min Act: -0.1700
Data Index: 892025 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19