Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2215 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.8092. Min Act: -0.1700
Data Index: 1282127 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.7154. Min Act: -0.1700
Data Index: 4469671 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.6842. Min Act: -0.1700
Data Index: 1141749 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.7154. Min Act: -0.1700
Data Index: 4408214 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.6529. Min Act: -0.1700
Data Index: 1855086 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.6529. Min Act: -0.1700
Data Index: 8169292 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5904. Min Act: -0.1700
Data Index: 89296 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.6217. Min Act: -0.1700
Data Index: 3854283 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.6217. Min Act: -0.1700
Data Index: 8487308 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5904. Min Act: -0.1700
Data Index: 7291316 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5904. Min Act: -0.1700
Data Index: 4042297 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5904. Min Act: -0.1700
Data Index: 1402911 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5904. Min Act: -0.1700
Data Index: 6214982 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5904. Min Act: -0.1700
Data Index: 2572516 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5592. Min Act: -0.1700
Data Index: 1312814 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5279. Min Act: -0.1700
Data Index: 6991267 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5279. Min Act: -0.1700
Data Index: 7657413 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.5279. Min Act: -0.1700
Data Index: 3171759 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.4967. Min Act: -0.1700
Data Index: 6041224 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8092. Min Range: -4.8092
Max Act: 4.4654. Min Act: -0.1700
Data Index: 4991620 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19