Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1886. Min Range: -5.1886
Max Act: 5.1886. Min Act: -0.1700
Data Index: 7736607 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1886. Min Range: -5.1886
Max Act: 5.0323. Min Act: -0.1700
Data Index: 3317559 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1886. Min Range: -5.1886
Max Act: 5.0323. Min Act: -0.1700
Data Index: 4011560 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.9698. Min Act: -0.1700
Data Index: 4738321 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.9698. Min Act: -0.1700
Data Index: 1490066 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.9073. Min Act: -0.1700
Data Index: 6786049 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.9073. Min Act: -0.1700
Data Index: 5325189 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.9073. Min Act: -0.1700
Data Index: 4981994 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8761. Min Act: -0.1700
Data Index: 8588205 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8761. Min Act: -0.1700
Data Index: 4772945 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8448. Min Act: -0.1700
Data Index: 4673239 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8448. Min Act: -0.1700
Data Index: 2737096 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8448. Min Act: -0.1700
Data Index: 6174362 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8448. Min Act: -0.1700
Data Index: 3412203 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8448. Min Act: -0.1700
Data Index: 1767494 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8136. Min Act: -0.1700
Data Index: 6405057 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8136. Min Act: -0.1700
Data Index: 6314585 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8136. Min Act: -0.1700
Data Index: 1181816 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8136. Min Act: -0.1700
Data Index: 7760408 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1886. Min Range: -5.1886
Max Act: 4.8136. Min Act: -0.1700
Data Index: 283064 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19