Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5574 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.8547. Min Act: -0.1700
Data Index: 31957 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.8547. Min Act: -0.1700
Data Index: 2059748 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.8234. Min Act: -0.1700
Data Index: 8433920 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.7608. Min Act: -0.1700
Data Index: 2732916 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.7921. Min Act: -0.1700
Data Index: 7044706 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.7296. Min Act: -0.1700
Data Index: 8051607 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6983. Min Act: -0.1700
Data Index: 6613986 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6983. Min Act: -0.1700
Data Index: 5332043 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6983. Min Act: -0.1700
Data Index: 8525594 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6983. Min Act: -0.1700
Data Index: 7154670 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6670. Min Act: -0.1700
Data Index: 912109 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6670. Min Act: -0.1700
Data Index: 6243087 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6670. Min Act: -0.1700
Data Index: 1898221 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6670. Min Act: -0.1700
Data Index: 5973326 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6670. Min Act: -0.1700
Data Index: 912721 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6357. Min Act: -0.1700
Data Index: 6429718 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6357. Min Act: -0.1700
Data Index: 4285720 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6357. Min Act: -0.1700
Data Index: 5458654 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6357. Min Act: -0.1700
Data Index: 5169204 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8547. Min Range: -3.8547
Max Act: 3.6357. Min Act: -0.1700
Data Index: 538279 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19