Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 750 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0690. Min Range: -5.0690
Max Act: 5.0690. Min Act: -0.1700
Data Index: 7228965 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0690. Min Range: -5.0690
Max Act: 5.0378. Min Act: -0.1700
Data Index: 6647400 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0690. Min Range: -5.0690
Max Act: 5.0065. Min Act: -0.1700
Data Index: 3313185 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.9753. Min Act: -0.1700
Data Index: 5799234 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0690. Min Range: -5.0690
Max Act: 5.0065. Min Act: -0.1700
Data Index: 2673888 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.9753. Min Act: -0.1700
Data Index: 3517691 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.9128. Min Act: -0.1700
Data Index: 5190067 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8815. Min Act: -0.1700
Data Index: 6098927 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8815. Min Act: -0.1700
Data Index: 6176206 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8815. Min Act: -0.1700
Data Index: 3353702 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8503. Min Act: -0.1700
Data Index: 3654261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8190. Min Act: -0.1700
Data Index: 650927 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8190. Min Act: -0.1700
Data Index: 5245756 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8503. Min Act: -0.1700
Data Index: 2817056 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.8190. Min Act: -0.1700
Data Index: 3964267 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7878. Min Act: -0.1700
Data Index: 7232557 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7878. Min Act: -0.1700
Data Index: 8428074 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7253. Min Act: -0.1700
Data Index: 59913 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7253. Min Act: -0.1700
Data Index: 7204636 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0690. Min Range: -5.0690
Max Act: 4.7565. Min Act: -0.1700
Data Index: 5144969 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19