Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.1943. Min Act: -0.1700
Data Index: 1816418 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.1444. Min Act: -0.1700
Data Index: 831435 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.1444. Min Act: -0.1700
Data Index: 2694772 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.1110. Min Act: -0.1700
Data Index: 3177972 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.1110. Min Act: -0.1700
Data Index: 7309342 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0943. Min Act: -0.1700
Data Index: 5954234 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.1110. Min Act: -0.1700
Data Index: 418416 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0775. Min Act: -0.1700
Data Index: 1843266 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0775. Min Act: -0.1700
Data Index: 5202704 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0607. Min Act: -0.1699
Data Index: 909697 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0271. Min Act: -0.1700
Data Index: 5208803 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0439. Min Act: -0.1700
Data Index: 3443601 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0439. Min Act: -0.1700
Data Index: 4727946 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0439. Min Act: -0.1700
Data Index: 4052512 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0439. Min Act: -0.1700
Data Index: 5105989 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0607. Min Act: -0.1700
Data Index: 1615135 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0439. Min Act: -0.1700
Data Index: 3508060 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0439. Min Act: -0.1700
Data Index: 5678480 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0439. Min Act: -0.1700
Data Index: 2703278 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1943. Min Range: -2.1943
Max Act: 2.0439. Min Act: -0.1700
Data Index: 4489662 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19