Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4055 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.9713. Min Act: -0.1700
Data Index: 2063015 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.8776. Min Act: -0.1700
Data Index: 8002039 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.8151. Min Act: -0.1700
Data Index: 1807513 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.8151. Min Act: -0.1700
Data Index: 6187648 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.8151. Min Act: -0.1700
Data Index: 5931653 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.6588. Min Act: -0.1700
Data Index: 7119106 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.6588. Min Act: -0.1700
Data Index: 3183106 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.6276. Min Act: -0.1700
Data Index: 5486885 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5963. Min Act: -0.1700
Data Index: 6727633 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5651. Min Act: -0.1700
Data Index: 6919998 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5651. Min Act: -0.1700
Data Index: 6600142 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5651. Min Act: -0.1700
Data Index: 5443952 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5026. Min Act: -0.1700
Data Index: 2208259 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5338. Min Act: -0.1700
Data Index: 6074068 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5026. Min Act: -0.1700
Data Index: 1113656 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5026. Min Act: -0.1700
Data Index: 8680136 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5338. Min Act: -0.1700
Data Index: 5835308 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.5338. Min Act: -0.1700
Data Index: 7899622 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.4713. Min Act: -0.1700
Data Index: 698889 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9713. Min Range: -6.9713
Max Act: 6.4713. Min Act: -0.1700
Data Index: 6012502 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19