Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.2033. Min Act: -0.1700
Data Index: 4045458 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.1095. Min Act: -0.1700
Data Index: 3290699 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.1095. Min Act: -0.1700
Data Index: 5418636 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4469170 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.1095. Min Act: -0.1700
Data Index: 8542112 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0783. Min Act: -0.1700
Data Index: 2981371 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0470. Min Act: -0.1700
Data Index: 5193113 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0470. Min Act: -0.1700
Data Index: 8768202 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0470. Min Act: -0.1700
Data Index: 8538416 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0783. Min Act: -0.1700
Data Index: 3894448 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0470. Min Act: -0.1700
Data Index: 5663159 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0158. Min Act: -0.1700
Data Index: 2799246 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0158. Min Act: -0.1700
Data Index: 4413584 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2033. Min Range: -5.2033
Max Act: 4.9845. Min Act: -0.1700
Data Index: 7074530 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2033. Min Range: -5.2033
Max Act: 4.9845. Min Act: -0.1700
Data Index: 1508636 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2033. Min Range: -5.2033
Max Act: 5.0158. Min Act: -0.1700
Data Index: 4444693 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2033. Min Range: -5.2033
Max Act: 4.9845. Min Act: -0.1700
Data Index: 1582263 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2033. Min Range: -5.2033
Max Act: 4.9533. Min Act: -0.1700
Data Index: 3624842 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2033. Min Range: -5.2033
Max Act: 4.9220. Min Act: -0.1700
Data Index: 1009209 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2033. Min Range: -5.2033
Max Act: 4.8908. Min Act: -0.1700
Data Index: 7866101 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19