Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4796. Min Range: -4.4796
Max Act: 4.4796. Min Act: -0.1700
Data Index: 6587640 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4796. Min Range: -4.4796
Max Act: 4.3233. Min Act: -0.1700
Data Index: 8023193 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4796. Min Range: -4.4796
Max Act: 4.1983. Min Act: -0.1700
Data Index: 7508518 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4796. Min Range: -4.4796
Max Act: 4.0421. Min Act: -0.1700
Data Index: 479914 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4796. Min Range: -4.4796
Max Act: 4.0108. Min Act: -0.1700
Data Index: 3317667 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.9952. Min Act: -0.1700
Data Index: 2334182 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.9170. Min Act: -0.1700
Data Index: 5045601 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.8857. Min Act: -0.1700
Data Index: 583588 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.8857. Min Act: -0.1700
Data Index: 3941301 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.8232. Min Act: -0.1700
Data Index: 3711254 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.8545. Min Act: -0.1700
Data Index: 638264 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.7919. Min Act: -0.1700
Data Index: 4763127 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.8076. Min Act: -0.1700
Data Index: 757481 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.7450. Min Act: -0.1700
Data Index: 4348496 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.8076. Min Act: -0.1700
Data Index: 2293309 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.7450. Min Act: -0.1700
Data Index: 4732190 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.7450. Min Act: -0.1700
Data Index: 3114957 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.7606. Min Act: -0.1700
Data Index: 858899 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.7450. Min Act: -0.1700
Data Index: 2550723 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4796. Min Range: -4.4796
Max Act: 3.7137. Min Act: -0.1700
Data Index: 2064785 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19