Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2424 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.8108. Min Act: -0.1700
Data Index: 6897776 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.7795. Min Act: -0.1700
Data Index: 5235787 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.6233. Min Act: -0.1700
Data Index: 3722366 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.4045. Min Act: -0.1700
Data Index: 1389189 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.4045. Min Act: -0.1700
Data Index: 3423463 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.4045. Min Act: -0.1700
Data Index: 4602570 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.3733. Min Act: -0.1700
Data Index: 8423020 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.2795. Min Act: -0.1700
Data Index: 3517362 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.2795. Min Act: -0.1700
Data Index: 4555953 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.2795. Min Act: -0.1700
Data Index: 3903498 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.2170. Min Act: -0.1700
Data Index: 1816818 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.2483. Min Act: -0.1700
Data Index: 7600428 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.2170. Min Act: -0.1700
Data Index: 7424539 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.2170. Min Act: -0.1700
Data Index: 3606610 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.2170. Min Act: -0.1700
Data Index: 3678727 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.1858. Min Act: -0.1700
Data Index: 5204248 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.1858. Min Act: -0.1700
Data Index: 5326840 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.1545. Min Act: -0.1700
Data Index: 6343093 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.1545. Min Act: -0.1700
Data Index: 7129441 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8108. Min Range: -6.8108
Max Act: 6.1233. Min Act: -0.1700
Data Index: 3264134 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19