Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.8054. Min Act: -0.1700
Data Index: 3215881 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.7429. Min Act: -0.1700
Data Index: 2858014 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.6491. Min Act: -0.1700
Data Index: 1176706 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.6179. Min Act: -0.1700
Data Index: 3063625 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.6179. Min Act: -0.1700
Data Index: 2305058 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.5241. Min Act: -0.1700
Data Index: 5226126 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4929. Min Act: -0.1700
Data Index: 4961160 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4929. Min Act: -0.1700
Data Index: 8492976 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4304. Min Act: -0.1700
Data Index: 2530423 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4616. Min Act: -0.1700
Data Index: 3934078 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4616. Min Act: -0.1700
Data Index: 54945 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4616. Min Act: -0.1700
Data Index: 3589560 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4304. Min Act: -0.1700
Data Index: 5248448 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4616. Min Act: -0.1700
Data Index: 2329280 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4304. Min Act: -0.1700
Data Index: 4899412 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4304. Min Act: -0.1700
Data Index: 6606839 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.3991. Min Act: -0.1700
Data Index: 1655644 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.4616. Min Act: -0.1700
Data Index: 8397128 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.3991. Min Act: -0.1700
Data Index: 1016798 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8054. Min Range: -4.8054
Max Act: 4.3991. Min Act: -0.1700
Data Index: 7263803 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19