Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4524. Min Range: -4.4524
Max Act: 4.4524. Min Act: -0.1700
Data Index: 8212091 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4524. Min Range: -4.4524
Max Act: 4.2024. Min Act: -0.1700
Data Index: 4443605 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4524. Min Range: -4.4524
Max Act: 4.1087. Min Act: -0.1700
Data Index: 5512300 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4524. Min Range: -4.4524
Max Act: 4.0774. Min Act: -0.1700
Data Index: 262428 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4524. Min Range: -4.4524
Max Act: 4.0774. Min Act: -0.1700
Data Index: 2403774 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4524. Min Range: -4.4524
Max Act: 4.0149. Min Act: -0.1700
Data Index: 5130055 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4524. Min Range: -4.4524
Max Act: 4.0149. Min Act: -0.1700
Data Index: 6376189 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.9836. Min Act: -0.1700
Data Index: 8122450 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.9524. Min Act: -0.1700
Data Index: 6704183 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.9524. Min Act: -0.1700
Data Index: 7327250 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.8898. Min Act: -0.1700
Data Index: 6784143 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.9211. Min Act: -0.1700
Data Index: 977726 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.8898. Min Act: -0.1700
Data Index: 8271499 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.9211. Min Act: -0.1700
Data Index: 5551613 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.8898. Min Act: -0.1700
Data Index: 4021617 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.8586. Min Act: -0.1700
Data Index: 6961828 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.8586. Min Act: -0.1700
Data Index: 2658046 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.8273. Min Act: -0.1700
Data Index: 5213317 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.8586. Min Act: -0.1700
Data Index: 1979418 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4524. Min Range: -4.4524
Max Act: 3.8586. Min Act: -0.1700
Data Index: 4252576 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19