Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4966 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.4561. Min Act: -0.1700
Data Index: 5173477 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.4248. Min Act: -0.1700
Data Index: 3434834 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.3621. Min Act: -0.1700
Data Index: 5412375 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.3464. Min Act: -0.1700
Data Index: 5395559 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.3307. Min Act: -0.1700
Data Index: 1629961 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.3150. Min Act: -0.1700
Data Index: 4031852 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2993. Min Act: -0.1700
Data Index: 4169598 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2836. Min Act: -0.1700
Data Index: 5150498 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2993. Min Act: -0.1700
Data Index: 4904785 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2993. Min Act: -0.1700
Data Index: 5091575 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2836. Min Act: -0.1700
Data Index: 6124539 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2836. Min Act: -0.1700
Data Index: 6314685 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2836. Min Act: -0.1700
Data Index: 4878313 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2836. Min Act: -0.1700
Data Index: 2492623 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2836. Min Act: -0.1700
Data Index: 5061894 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2836. Min Act: -0.1700
Data Index: 8205127 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2679. Min Act: -0.1700
Data Index: 1939539 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2679. Min Act: -0.1700
Data Index: 6712650 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2679. Min Act: -0.1700
Data Index: 6007279 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4561. Min Range: -3.4561
Max Act: 3.2522. Min Act: -0.1700
Data Index: 6268022 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19