Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1887. Min Range: -9.1887
Max Act: 9.1887. Min Act: -0.1700
Data Index: 1555284 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1887. Min Range: -9.1887
Max Act: 9.0637. Min Act: -0.1700
Data Index: 1267599 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1887. Min Range: -9.1887
Max Act: 9.0012. Min Act: -0.1700
Data Index: 7200826 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1887. Min Range: -9.1887
Max Act: 9.0012. Min Act: -0.1700
Data Index: 3488067 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.8762. Min Act: -0.1700
Data Index: 2425329 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.8762. Min Act: -0.1700
Data Index: 4211727 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.8762. Min Act: -0.1700
Data Index: 2027374 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.8762. Min Act: -0.1700
Data Index: 2766203 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.8137. Min Act: -0.1700
Data Index: 4439620 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.8137. Min Act: -0.1700
Data Index: 2296979 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.8137. Min Act: -0.1700
Data Index: 1005577 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.6887. Min Act: -0.1700
Data Index: 1975348 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.7512. Min Act: -0.1700
Data Index: 664763 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.8137. Min Act: -0.1700
Data Index: 4533568 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.7512. Min Act: -0.1700
Data Index: 4826634 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.7512. Min Act: -0.1700
Data Index: 1601441 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.7512. Min Act: -0.1700
Data Index: 6320815 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.7512. Min Act: -0.1700
Data Index: 7599978 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.7512. Min Act: -0.1700
Data Index: 2528988 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1887. Min Range: -9.1887
Max Act: 8.7512. Min Act: -0.1700
Data Index: 7604557 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19