Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5883 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0923. Min Range: -5.0923
Max Act: 5.0923. Min Act: -0.1700
Data Index: 760202 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.8110. Min Act: -0.1700
Data Index: 5031035 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.8110. Min Act: -0.1700
Data Index: 187219 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.7798. Min Act: -0.1700
Data Index: 6569245 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.7485. Min Act: -0.1700
Data Index: 2543993 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.7173. Min Act: -0.1700
Data Index: 6758953 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.7173. Min Act: -0.1700
Data Index: 838769 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.6860. Min Act: -0.1700
Data Index: 4764459 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.6860. Min Act: -0.1700
Data Index: 2244204 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.6860. Min Act: -0.1700
Data Index: 756509 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.6860. Min Act: -0.1700
Data Index: 4387272 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.6548. Min Act: -0.1700
Data Index: 3224165 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.6235. Min Act: -0.1700
Data Index: 268437 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.5923. Min Act: -0.1700
Data Index: 4912117 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.6235. Min Act: -0.1700
Data Index: 6652074 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.5610. Min Act: -0.1700
Data Index: 3798534 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.5923. Min Act: -0.1700
Data Index: 6937981 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.5610. Min Act: -0.1700
Data Index: 3733832 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.5923. Min Act: -0.1700
Data Index: 655386 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0923. Min Range: -5.0923
Max Act: 4.5298. Min Act: -0.1700
Data Index: 138875 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19