Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 85 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.3681. Min Act: -0.1700
Data Index: 5703800 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.3681. Min Act: -0.1700
Data Index: 1925622 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.3369. Min Act: -0.1700
Data Index: 2058171 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.3369. Min Act: -0.1700
Data Index: 4854641 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.2744. Min Act: -0.1700
Data Index: 8677876 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.3056. Min Act: -0.1700
Data Index: 7094094 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.2744. Min Act: -0.1700
Data Index: 705202 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.1806. Min Act: -0.1700
Data Index: 705204 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.2119. Min Act: -0.1700
Data Index: 519044 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.2119. Min Act: -0.1700
Data Index: 8813871 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.1806. Min Act: -0.1700
Data Index: 7379348 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.1494. Min Act: -0.1700
Data Index: 7379349 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.1806. Min Act: -0.1700
Data Index: 2449614 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.1494. Min Act: -0.1700
Data Index: 3318983 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.0868. Min Act: -0.1700
Data Index: 5055962 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.1181. Min Act: -0.1700
Data Index: 5526649 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.0868. Min Act: -0.1700
Data Index: 8153440 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.0868. Min Act: -0.1700
Data Index: 1677358 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.0556. Min Act: -0.1700
Data Index: 8462981 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3681. Min Range: -4.3681
Max Act: 4.0868. Min Act: -0.1700
Data Index: 8543867 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19