Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.2873. Min Act: -0.1700
Data Index: 7487861 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.1458. Min Act: -0.1700
Data Index: 1130837 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0986. Min Act: -0.1700
Data Index: 3281676 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0828. Min Act: -0.1700
Data Index: 7179836 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0828. Min Act: -0.1700
Data Index: 5220837 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0670. Min Act: -0.1700
Data Index: 8717145 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0670. Min Act: -0.1700
Data Index: 3166001 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0513. Min Act: -0.1700
Data Index: 6050574 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0513. Min Act: -0.1700
Data Index: 1562783 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0513. Min Act: -0.1700
Data Index: 3885052 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0513. Min Act: -0.1700
Data Index: 6553824 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0513. Min Act: -0.1700
Data Index: 6162394 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0355. Min Act: -0.1700
Data Index: 6577138 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0355. Min Act: -0.1700
Data Index: 3854310 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0355. Min Act: -0.1700
Data Index: 6155573 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0355. Min Act: -0.1700
Data Index: 1732178 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0355. Min Act: -0.1700
Data Index: 6162393 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0197. Min Act: -0.1700
Data Index: 2149869 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0039. Min Act: -0.1700
Data Index: 3455870 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2873. Min Range: -3.2873
Max Act: 3.0197. Min Act: -0.1700
Data Index: 4329069 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19