Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.7574. Min Act: -0.1700
Data Index: 4436656 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.6637. Min Act: -0.1700
Data Index: 8091466 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.5074. Min Act: -0.1700
Data Index: 3835373 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.5387. Min Act: -0.1700
Data Index: 7006932 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.5074. Min Act: -0.1700
Data Index: 341948 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.5074. Min Act: -0.1700
Data Index: 7674255 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.4762. Min Act: -0.1700
Data Index: 2225879 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.4449. Min Act: -0.1700
Data Index: 2533230 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.4137. Min Act: -0.1700
Data Index: 7677948 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.3824. Min Act: -0.1700
Data Index: 4826125 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.3824. Min Act: -0.1700
Data Index: 3748621 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.3199. Min Act: -0.1700
Data Index: 1027235 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.3199. Min Act: -0.1700
Data Index: 2673949 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.3512. Min Act: -0.1700
Data Index: 3175273 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.2887. Min Act: -0.1700
Data Index: 6030751 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.2574. Min Act: -0.1700
Data Index: 2273290 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.2574. Min Act: -0.1700
Data Index: 6545552 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.2887. Min Act: -0.1700
Data Index: 4880520 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.2574. Min Act: -0.1700
Data Index: 8017361 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7574. Min Range: -5.7574
Max Act: 5.2574. Min Act: -0.1700
Data Index: 7316803 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19