Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 921 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.4706. Min Act: -0.1700
Data Index: 4053861 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.4706. Min Act: -0.1700
Data Index: 8805241 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.4394. Min Act: -0.1700
Data Index: 1232984 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.4394. Min Act: -0.1700
Data Index: 6707133 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.4394. Min Act: -0.1700
Data Index: 2904286 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.4081. Min Act: -0.1700
Data Index: 1928460 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.4081. Min Act: -0.1700
Data Index: 410813 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3769. Min Act: -0.1700
Data Index: 5214695 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3769. Min Act: -0.1700
Data Index: 4047575 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3769. Min Act: -0.1700
Data Index: 2591804 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3769. Min Act: -0.1700
Data Index: 2077685 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3769. Min Act: -0.1700
Data Index: 8258086 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.4081. Min Act: -0.1700
Data Index: 3777175 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3769. Min Act: -0.1700
Data Index: 3422830 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3456. Min Act: -0.1700
Data Index: 1493761 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3456. Min Act: -0.1700
Data Index: 3104901 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3144. Min Act: -0.1700
Data Index: 708417 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3456. Min Act: -0.1700
Data Index: 5044447 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3456. Min Act: -0.1700
Data Index: 198692 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4706. Min Range: -4.4706
Max Act: 4.3144. Min Act: -0.1700
Data Index: 4142345 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19