Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.5105. Min Act: -0.1700
Data Index: 3815600 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.3230. Min Act: -0.1700
Data Index: 6183342 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.2918. Min Act: -0.1700
Data Index: 4624222 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.2605. Min Act: -0.1700
Data Index: 7329786 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.2605. Min Act: -0.1700
Data Index: 2409627 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.2605. Min Act: -0.1700
Data Index: 3874719 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.2918. Min Act: -0.1700
Data Index: 487196 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.2293. Min Act: -0.1700
Data Index: 440654 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1980. Min Act: -0.1700
Data Index: 369460 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1668. Min Act: -0.1700
Data Index: 4349717 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1668. Min Act: -0.1700
Data Index: 1259595 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1043. Min Act: -0.1700
Data Index: 6670293 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1043. Min Act: -0.1700
Data Index: 3372770 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1043. Min Act: -0.1700
Data Index: 5984023 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1043. Min Act: -0.1700
Data Index: 2919983 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.0730. Min Act: -0.1700
Data Index: 6904884 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1043. Min Act: -0.1700
Data Index: 1690270 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1043. Min Act: -0.1700
Data Index: 1287205 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.0730. Min Act: -0.1700
Data Index: 500222 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5105. Min Range: -4.5105
Max Act: 4.1043. Min Act: -0.1700
Data Index: 7773973 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19