Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.9582. Min Act: -0.1700
Data Index: 4223021 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.9269. Min Act: -0.1700
Data Index: 6193320 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.9269. Min Act: -0.1700
Data Index: 6193321 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.8957. Min Act: -0.1700
Data Index: 4511819 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.8644. Min Act: -0.1700
Data Index: 2259738 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.8332. Min Act: -0.1700
Data Index: 1421201 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.8019. Min Act: -0.1700
Data Index: 5421609 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.8019. Min Act: -0.1700
Data Index: 3818434 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7394. Min Act: -0.1700
Data Index: 5437005 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7394. Min Act: -0.1700
Data Index: 4072693 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7707. Min Act: -0.1700
Data Index: 3295607 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.8019. Min Act: -0.1700
Data Index: 2259737 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7707. Min Act: -0.1700
Data Index: 6341949 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7707. Min Act: -0.1700
Data Index: 6956420 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7707. Min Act: -0.1700
Data Index: 4223019 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7082. Min Act: -0.1700
Data Index: 2528045 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7394. Min Act: -0.1700
Data Index: 5848556 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7394. Min Act: -0.1700
Data Index: 4908565 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7394. Min Act: -0.1700
Data Index: 3187777 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.7394. Min Act: -0.1700
Data Index: 2735785 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19