Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3731 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.9054. Min Act: -0.1700
Data Index: 5711750 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.7804. Min Act: -0.1700
Data Index: 1435672 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.6867. Min Act: -0.1700
Data Index: 123004 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.6242. Min Act: -0.1700
Data Index: 1672329 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5929. Min Act: -0.1700
Data Index: 7626608 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.6242. Min Act: -0.1700
Data Index: 8474919 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.6242. Min Act: -0.1700
Data Index: 6117118 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5929. Min Act: -0.1700
Data Index: 4213220 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5929. Min Act: -0.1700
Data Index: 5834657 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5617. Min Act: -0.1700
Data Index: 6854871 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5617. Min Act: -0.1700
Data Index: 7082631 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5304. Min Act: -0.1700
Data Index: 3360948 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5929. Min Act: -0.1700
Data Index: 1131868 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5617. Min Act: -0.1700
Data Index: 3704219 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.5617. Min Act: -0.1700
Data Index: 522568 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.4367. Min Act: -0.1700
Data Index: 5374507 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.4367. Min Act: -0.1700
Data Index: 3175181 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.4679. Min Act: -0.1700
Data Index: 3535758 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.4367. Min Act: -0.1700
Data Index: 2928232 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9054. Min Range: -5.9054
Max Act: 5.4679. Min Act: -0.1700
Data Index: 3201551 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19