Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.6171. Min Act: -0.1700
Data Index: 3561867 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.4296. Min Act: -0.1700
Data Index: 7176324 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.3358. Min Act: -0.1700
Data Index: 1550931 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.3358. Min Act: -0.1700
Data Index: 2715506 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2733. Min Act: -0.1700
Data Index: 860864 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2733. Min Act: -0.1700
Data Index: 7885400 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2733. Min Act: -0.1700
Data Index: 4268325 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2733. Min Act: -0.1700
Data Index: 8573227 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2733. Min Act: -0.1700
Data Index: 4461613 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2733. Min Act: -0.1700
Data Index: 1841294 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2733. Min Act: -0.1700
Data Index: 2687019 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2421. Min Act: -0.1700
Data Index: 6083987 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2733. Min Act: -0.1700
Data Index: 5136177 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2421. Min Act: -0.1700
Data Index: 8804669 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2421. Min Act: -0.1700
Data Index: 8743154 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2421. Min Act: -0.1700
Data Index: 3573729 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2421. Min Act: -0.1700
Data Index: 1688220 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2108. Min Act: -0.1700
Data Index: 267999 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2108. Min Act: -0.1700
Data Index: 2566076 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6171. Min Range: -5.6171
Max Act: 5.2108. Min Act: -0.1700
Data Index: 3542592 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19