Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4685. Min Range: -7.4685
Max Act: 7.4685. Min Act: -0.1700
Data Index: 5570359 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4685. Min Range: -7.4685
Max Act: 7.0622. Min Act: -0.1700
Data Index: 6541129 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.7810. Min Act: -0.1700
Data Index: 8759989 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.7497. Min Act: -0.1700
Data Index: 878443 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.7185. Min Act: -0.1700
Data Index: 8723187 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.7185. Min Act: -0.1700
Data Index: 1912667 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.7185. Min Act: -0.1700
Data Index: 290121 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.7185. Min Act: -0.1700
Data Index: 5292084 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.7185. Min Act: -0.1700
Data Index: 1389160 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.6872. Min Act: -0.1700
Data Index: 5374878 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.6560. Min Act: -0.1700
Data Index: 6552639 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.6560. Min Act: -0.1700
Data Index: 5383150 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.5935. Min Act: -0.1700
Data Index: 6646187 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.5622. Min Act: -0.1700
Data Index: 8801047 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.5622. Min Act: -0.1700
Data Index: 5483665 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.4997. Min Act: -0.1700
Data Index: 4979131 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.4997. Min Act: -0.1700
Data Index: 2976157 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.4997. Min Act: -0.1700
Data Index: 8416697 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.4685. Min Act: -0.1700
Data Index: 6466710 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4685. Min Range: -7.4685
Max Act: 6.4685. Min Act: -0.1700
Data Index: 1918649 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19