Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.4751. Min Act: -0.1700
Data Index: 4455967 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.5064. Min Act: -0.1700
Data Index: 6727354 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.4439. Min Act: -0.1700
Data Index: 7939568 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.4439. Min Act: -0.1700
Data Index: 5477096 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.4126. Min Act: -0.1700
Data Index: 8251981 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.4439. Min Act: -0.1700
Data Index: 2969783 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.4126. Min Act: -0.1700
Data Index: 3406410 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.2564. Min Act: -0.1700
Data Index: 52107 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.2251. Min Act: -0.1700
Data Index: 6198820 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.2251. Min Act: -0.1700
Data Index: 8526702 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.1939. Min Act: -0.1700
Data Index: 2629253 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.1939. Min Act: -0.1700
Data Index: 3016313 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.1626. Min Act: -0.1700
Data Index: 7582264 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.1314. Min Act: -0.1700
Data Index: 798492 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.1314. Min Act: -0.1700
Data Index: 7891188 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.1001. Min Act: -0.1700
Data Index: 7752494 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.0689. Min Act: -0.1700
Data Index: 6938159 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.0689. Min Act: -0.1700
Data Index: 3398288 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.1001. Min Act: -0.1700
Data Index: 766599 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5064. Min Range: -6.5064
Max Act: 6.1001. Min Act: -0.1700
Data Index: 132478 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19