Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4621 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.2777. Min Act: -0.1700
Data Index: 4121134 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.1527. Min Act: -0.1700
Data Index: 3088517 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.1214. Min Act: -0.1700
Data Index: 3589972 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.0902. Min Act: -0.1700
Data Index: 3331628 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.0902. Min Act: -0.1700
Data Index: 3070355 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.0902. Min Act: -0.1700
Data Index: 8819774 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.0589. Min Act: -0.1700
Data Index: 2325740 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.0589. Min Act: -0.1700
Data Index: 8744761 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2777. Min Range: -4.2777
Max Act: 4.0276. Min Act: -0.1700
Data Index: 8744762 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9964. Min Act: -0.1700
Data Index: 669362 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9964. Min Act: -0.1700
Data Index: 3934498 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9964. Min Act: -0.1700
Data Index: 2055888 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9964. Min Act: -0.1700
Data Index: 5466516 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9651. Min Act: -0.1700
Data Index: 340728 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9651. Min Act: -0.1700
Data Index: 7254082 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9651. Min Act: -0.1700
Data Index: 3070356 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9964. Min Act: -0.1700
Data Index: 3694516 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9651. Min Act: -0.1700
Data Index: 8655264 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9651. Min Act: -0.1700
Data Index: 7755933 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2777. Min Range: -4.2777
Max Act: 3.9026. Min Act: -0.1700
Data Index: 1637758 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19