Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4750 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.5081. Min Act: -0.1700
Data Index: 8207243 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.4456. Min Act: -0.1700
Data Index: 7298557 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.4143. Min Act: -0.1700
Data Index: 6249994 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.4456. Min Act: -0.1700
Data Index: 79150 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.4143. Min Act: -0.1700
Data Index: 2727297 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.3518. Min Act: -0.1700
Data Index: 6010521 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.3518. Min Act: -0.1700
Data Index: 5695872 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.2893. Min Act: -0.1700
Data Index: 2207039 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.2581. Min Act: -0.1700
Data Index: 1478412 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.2581. Min Act: -0.1700
Data Index: 7447507 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.2268. Min Act: -0.1700
Data Index: 3720316 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.2268. Min Act: -0.1700
Data Index: 4778080 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.1956. Min Act: -0.1700
Data Index: 5144727 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.1643. Min Act: -0.1700
Data Index: 6089133 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.1956. Min Act: -0.1700
Data Index: 1336946 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.1956. Min Act: -0.1700
Data Index: 370219 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.1956. Min Act: -0.1700
Data Index: 7130242 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.1643. Min Act: -0.1700
Data Index: 1893024 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.1643. Min Act: -0.1700
Data Index: 3306497 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5081. Min Range: -6.5081
Max Act: 6.1331. Min Act: -0.1700
Data Index: 3365017 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19