Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4778 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1082. Min Range: -5.1082
Max Act: 5.1082. Min Act: -0.1700
Data Index: 7075406 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.7332. Min Act: -0.1700
Data Index: 4964151 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.6707. Min Act: -0.1700
Data Index: 4517167 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.6082. Min Act: -0.1700
Data Index: 7161931 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.5770. Min Act: -0.1700
Data Index: 3859687 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.5770. Min Act: -0.1700
Data Index: 4964150 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.5770. Min Act: -0.1700
Data Index: 4135545 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.5770. Min Act: -0.1700
Data Index: 481405 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.5457. Min Act: -0.1700
Data Index: 3046090 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.5145. Min Act: -0.1700
Data Index: 3582403 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.5145. Min Act: -0.1700
Data Index: 4517171 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.5145. Min Act: -0.1700
Data Index: 4819399 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.4832. Min Act: -0.1700
Data Index: 4941604 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.4832. Min Act: -0.1700
Data Index: 4517163 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.4520. Min Act: -0.1700
Data Index: 1500639 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.4207. Min Act: -0.1700
Data Index: 4517168 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.4520. Min Act: -0.1700
Data Index: 6055007 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.4520. Min Act: -0.1700
Data Index: 6636682 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.4520. Min Act: -0.1700
Data Index: 539445 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1082. Min Range: -5.1082
Max Act: 4.4520. Min Act: -0.1700
Data Index: 4819401 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19