Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 105 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5722. Min Act: -0.1700
Data Index: 890745 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5565. Min Act: -0.1700
Data Index: 6625602 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5565. Min Act: -0.1700
Data Index: 8550696 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5409. Min Act: -0.1700
Data Index: 1368152 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5409. Min Act: -0.1700
Data Index: 6939869 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5409. Min Act: -0.1700
Data Index: 653716 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5252. Min Act: -0.1700
Data Index: 8637683 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5096. Min Act: -0.1700
Data Index: 8807004 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5096. Min Act: -0.1700
Data Index: 919477 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5096. Min Act: -0.1700
Data Index: 2164918 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.5096. Min Act: -0.1700
Data Index: 8313545 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4782. Min Act: -0.1700
Data Index: 2516414 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4939. Min Act: -0.1700
Data Index: 4380220 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4939. Min Act: -0.1700
Data Index: 3216809 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4939. Min Act: -0.1700
Data Index: 2310390 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4782. Min Act: -0.1700
Data Index: 4353014 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4782. Min Act: -0.1700
Data Index: 3232436 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4939. Min Act: -0.1700
Data Index: 1486025 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4626. Min Act: -0.1700
Data Index: 8195534 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5722. Min Range: -3.5722
Max Act: 3.4626. Min Act: -0.1700
Data Index: 4455968 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19