Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6181. Min Range: -10.6181
Max Act: 10.6181. Min Act: -0.1700
Data Index: 2437385 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6181. Min Range: -10.6181
Max Act: 10.2431. Min Act: -0.1700
Data Index: 3575688 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6181. Min Range: -10.6181
Max Act: 10.0556. Min Act: -0.1700
Data Index: 4501235 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6181. Min Range: -10.6181
Max Act: 10.0556. Min Act: -0.1700
Data Index: 2252103 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.9931. Min Act: -0.1700
Data Index: 69594 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.9306. Min Act: -0.1700
Data Index: 7164284 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.9931. Min Act: -0.1700
Data Index: 5366426 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.8681. Min Act: -0.1700
Data Index: 4289493 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.8681. Min Act: -0.1700
Data Index: 2567877 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.8681. Min Act: -0.1700
Data Index: 7007593 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.7431. Min Act: -0.1700
Data Index: 7803249 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.8056. Min Act: -0.1700
Data Index: 6748858 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.7431. Min Act: -0.1700
Data Index: 5431795 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.8056. Min Act: -0.1700
Data Index: 2846277 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.7431. Min Act: -0.1700
Data Index: 3040327 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.6806. Min Act: -0.1700
Data Index: 392821 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.6806. Min Act: -0.1700
Data Index: 3582770 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.6181. Min Act: -0.1700
Data Index: 931414 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.6181. Min Act: -0.1700
Data Index: 342747 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6181. Min Range: -10.6181
Max Act: 9.5556. Min Act: -0.1700
Data Index: 590011 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19