Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1026. Min Range: -8.1026
Max Act: 8.1026. Min Act: -0.1700
Data Index: 4146812 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.5089. Min Act: -0.1700
Data Index: 7050571 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.4776. Min Act: -0.1700
Data Index: 1969397 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.4776. Min Act: -0.1700
Data Index: 5585978 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.4776. Min Act: -0.1700
Data Index: 6791965 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.4464. Min Act: -0.1700
Data Index: 2161138 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.4151. Min Act: -0.1700
Data Index: 6522419 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.3214. Min Act: -0.1700
Data Index: 8222303 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.3214. Min Act: -0.1700
Data Index: 2386787 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.2901. Min Act: -0.1700
Data Index: 2692042 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.2589. Min Act: -0.1700
Data Index: 6442179 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.2276. Min Act: -0.1700
Data Index: 864845 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.2276. Min Act: -0.1700
Data Index: 2734089 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.1339. Min Act: -0.1700
Data Index: 5154998 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.1964. Min Act: -0.1700
Data Index: 7235615 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.1339. Min Act: -0.1700
Data Index: 1823320 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.1026. Min Act: -0.1700
Data Index: 8166369 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.1026. Min Act: -0.1700
Data Index: 309238 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.0714. Min Act: -0.1700
Data Index: 3122322 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1026. Min Range: -8.1026
Max Act: 7.0714. Min Act: -0.1700
Data Index: 6488731 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19