Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.2396. Min Act: -0.1700
Data Index: 6716324 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1925. Min Act: -0.1700
Data Index: 8186752 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1925. Min Act: -0.1700
Data Index: 5706177 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1767. Min Act: -0.1700
Data Index: 1226813 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1767. Min Act: -0.1700
Data Index: 3622633 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1610. Min Act: -0.1700
Data Index: 510786 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1610. Min Act: -0.1700
Data Index: 5555329 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1453. Min Act: -0.1700
Data Index: 3622634 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1295. Min Act: -0.1700
Data Index: 3651966 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1295. Min Act: -0.1700
Data Index: 4330269 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1295. Min Act: -0.1700
Data Index: 6501174 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1138. Min Act: -0.1700
Data Index: 4382970 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.1138. Min Act: -0.1700
Data Index: 1341140 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.0980. Min Act: -0.1700
Data Index: 6785744 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.0980. Min Act: -0.1700
Data Index: 6663910 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.0980. Min Act: -0.1700
Data Index: 1414949 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.0980. Min Act: -0.1700
Data Index: 6744644 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.0822. Min Act: -0.1700
Data Index: 5506159 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.0822. Min Act: -0.1700
Data Index: 3236282 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2396. Min Range: -3.2396
Max Act: 3.0822. Min Act: -0.1700
Data Index: 2290565 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19