Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.3499. Min Act: -0.1700
Data Index: 452896 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.3186. Min Act: -0.1700
Data Index: 5642928 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.3186. Min Act: -0.1700
Data Index: 8361271 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.2561. Min Act: -0.1700
Data Index: 3073100 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.2248. Min Act: -0.1700
Data Index: 2130152 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.2248. Min Act: -0.1700
Data Index: 707743 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1936. Min Act: -0.1700
Data Index: 6813483 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1936. Min Act: -0.1700
Data Index: 7422466 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1936. Min Act: -0.1700
Data Index: 1354877 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1623. Min Act: -0.1700
Data Index: 2558570 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1623. Min Act: -0.1700
Data Index: 269266 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1623. Min Act: -0.1700
Data Index: 2140499 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1311. Min Act: -0.1700
Data Index: 7968732 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1311. Min Act: -0.1700
Data Index: 4452643 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1311. Min Act: -0.1700
Data Index: 6387075 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1311. Min Act: -0.1700
Data Index: 5539584 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.1311. Min Act: -0.1700
Data Index: 5847105 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.0998. Min Act: -0.1700
Data Index: 7869088 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.0998. Min Act: -0.1700
Data Index: 5076064 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3499. Min Range: -4.3499
Max Act: 4.0998. Min Act: -0.1700
Data Index: 2968749 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19