Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 111 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.4468. Min Act: -0.1700
Data Index: 2459688 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.4143. Min Act: -0.1700
Data Index: 5500233 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.4143. Min Act: -0.1700
Data Index: 4503146 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3816. Min Act: -0.1700
Data Index: 2647666 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3979. Min Act: -0.1700
Data Index: 5648134 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3816. Min Act: -0.1700
Data Index: 5010253 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3816. Min Act: -0.1700
Data Index: 616468 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3489. Min Act: -0.1700
Data Index: 1918689 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3325. Min Act: -0.1700
Data Index: 230190 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3325. Min Act: -0.1700
Data Index: 452635 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3325. Min Act: -0.1700
Data Index: 1445990 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3161. Min Act: -0.1700
Data Index: 4312360 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.3161. Min Act: -0.1700
Data Index: 1428240 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.2996. Min Act: -0.1700
Data Index: 4952748 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.2996. Min Act: -0.1700
Data Index: 3964244 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.2832. Min Act: -0.1700
Data Index: 4853343 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.2996. Min Act: -0.1700
Data Index: 5886286 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.2832. Min Act: -0.1700
Data Index: 5834489 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.2996. Min Act: -0.1700
Data Index: 4690471 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4468. Min Range: -2.4468
Max Act: 2.2667. Min Act: -0.1700
Data Index: 1893488 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19