Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1582 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.3946. Min Act: -0.1700
Data Index: 4317734 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2696. Min Act: -0.1700
Data Index: 610502 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.3008. Min Act: -0.1700
Data Index: 7020763 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.3008. Min Act: -0.1700
Data Index: 970064 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2383. Min Act: -0.1700
Data Index: 5600208 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2383. Min Act: -0.1700
Data Index: 5514696 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2383. Min Act: -0.1700
Data Index: 6170693 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2383. Min Act: -0.1700
Data Index: 2394785 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2383. Min Act: -0.1700
Data Index: 6423518 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2071. Min Act: -0.1700
Data Index: 3888717 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2071. Min Act: -0.1700
Data Index: 2066340 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.1758. Min Act: -0.1700
Data Index: 1830109 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.1446. Min Act: -0.1700
Data Index: 2894176 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.1758. Min Act: -0.1700
Data Index: 785092 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.1446. Min Act: -0.1700
Data Index: 4767459 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.2071. Min Act: -0.1700
Data Index: 1568472 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.1758. Min Act: -0.1700
Data Index: 4268786 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.1446. Min Act: -0.1700
Data Index: 80520 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.1446. Min Act: -0.1700
Data Index: 5902542 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3946. Min Range: -4.3946
Max Act: 4.1758. Min Act: -0.1700
Data Index: 4450505 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19