Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.6095. Min Act: -0.1700
Data Index: 5394203 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.5783. Min Act: -0.1700
Data Index: 1891778 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.3283. Min Act: -0.1700
Data Index: 5825947 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.3283. Min Act: -0.1700
Data Index: 4518237 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.3283. Min Act: -0.1700
Data Index: 1789750 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.2970. Min Act: -0.1700
Data Index: 8019450 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.2970. Min Act: -0.1700
Data Index: 7752017 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.2658. Min Act: -0.1700
Data Index: 5394204 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.2658. Min Act: -0.1700
Data Index: 7626775 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.2033. Min Act: -0.1700
Data Index: 157049 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.2033. Min Act: -0.1700
Data Index: 7301947 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.2033. Min Act: -0.1700
Data Index: 5781237 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.1720. Min Act: -0.1700
Data Index: 3813832 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.1720. Min Act: -0.1700
Data Index: 7752016 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.1408. Min Act: -0.1700
Data Index: 7276839 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4323966 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4242145 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.1408. Min Act: -0.1700
Data Index: 5787909 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.0783. Min Act: -0.1700
Data Index: 1871909 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6095. Min Range: -5.6095
Max Act: 5.0783. Min Act: -0.1700
Data Index: 485320 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19