Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1467 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.8080. Min Act: -0.1700
Data Index: 3465940 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.6517. Min Act: -0.1700
Data Index: 886945 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.5892. Min Act: -0.1700
Data Index: 85365 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.5580. Min Act: -0.1700
Data Index: 4102529 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.5580. Min Act: -0.1700
Data Index: 7088601 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4955. Min Act: -0.1700
Data Index: 2586982 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4642. Min Act: -0.1700
Data Index: 5872472 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4642. Min Act: -0.1700
Data Index: 1403703 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4330. Min Act: -0.1700
Data Index: 3084581 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4955. Min Act: -0.1700
Data Index: 556135 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4330. Min Act: -0.1700
Data Index: 4532555 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4330. Min Act: -0.1700
Data Index: 1169489 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4330. Min Act: -0.1700
Data Index: 841296 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.3705. Min Act: -0.1700
Data Index: 6950579 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4017. Min Act: -0.1700
Data Index: 7543395 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4017. Min Act: -0.1700
Data Index: 5545879 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4017. Min Act: -0.1700
Data Index: 7956097 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4017. Min Act: -0.1700
Data Index: 8182218 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4017. Min Act: -0.1700
Data Index: 8750608 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8080. Min Range: -4.8080
Max Act: 4.4017. Min Act: -0.1700
Data Index: 8828620 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19