Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 395 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.8161. Min Act: -0.1700
Data Index: 8153203 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7849. Min Act: -0.1700
Data Index: 91511 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7536. Min Act: -0.1700
Data Index: 3678118 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7849. Min Act: -0.1700
Data Index: 3999489 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7224. Min Act: -0.1700
Data Index: 5549799 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6286. Min Act: -0.1700
Data Index: 644140 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 5825907 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 8691636 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 4740706 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 3412584 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5036. Min Act: -0.1700
Data Index: 3893311 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5036. Min Act: -0.1700
Data Index: 645464 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 6279190 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4724. Min Act: -0.1700
Data Index: 7392494 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4724. Min Act: -0.1700
Data Index: 6943376 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4724. Min Act: -0.1700
Data Index: 8811276 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4724. Min Act: -0.1700
Data Index: 4253967 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4099. Min Act: -0.1700
Data Index: 959362 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4099. Min Act: -0.1700
Data Index: 6759869 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4411. Min Act: -0.1700
Data Index: 5993222 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19