Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1469. Min Range: -3.1469
Max Act: 3.1469. Min Act: -0.1700
Data Index: 6444526 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1469. Min Range: -3.1469
Max Act: 3.0050. Min Act: -0.1700
Data Index: 4675084 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.9575. Min Act: -0.1700
Data Index: 7089915 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.9417. Min Act: -0.1700
Data Index: 4557260 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.9417. Min Act: -0.1700
Data Index: 1336752 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.9259. Min Act: -0.1700
Data Index: 7691231 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.9100. Min Act: -0.1700
Data Index: 598999 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8942. Min Act: -0.1700
Data Index: 4069403 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8624. Min Act: -0.1700
Data Index: 7046848 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8783. Min Act: -0.1700
Data Index: 6873211 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8306. Min Act: -0.1700
Data Index: 3802591 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8465. Min Act: -0.1700
Data Index: 7566026 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8306. Min Act: -0.1700
Data Index: 6212163 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8147. Min Act: -0.1700
Data Index: 2348415 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8147. Min Act: -0.1700
Data Index: 3325459 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8465. Min Act: -0.1700
Data Index: 4359314 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8147. Min Act: -0.1700
Data Index: 2238296 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.7988. Min Act: -0.1700
Data Index: 6893033 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8147. Min Act: -0.1700
Data Index: 7690241 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1469. Min Range: -3.1469
Max Act: 2.8147. Min Act: -0.1700
Data Index: 6012105 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19