Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1400 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.4142. Min Act: -0.1700
Data Index: 4246318 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.3517. Min Act: -0.1700
Data Index: 4246321 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.2892. Min Act: -0.1700
Data Index: 2713378 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.2892. Min Act: -0.1700
Data Index: 4246316 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.2580. Min Act: -0.1700
Data Index: 4246313 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.2267. Min Act: -0.1700
Data Index: 5645731 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.1330. Min Act: -0.1700
Data Index: 1844880 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.1330. Min Act: -0.1700
Data Index: 400974 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.1017. Min Act: -0.1700
Data Index: 4246319 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.1017. Min Act: -0.1700
Data Index: 5085949 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.1017. Min Act: -0.1700
Data Index: 4246315 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0705. Min Act: -0.1700
Data Index: 1652466 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0705. Min Act: -0.1700
Data Index: 4246314 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0392. Min Act: -0.1700
Data Index: 1819906 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0705. Min Act: -0.1700
Data Index: 477054 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0392. Min Act: -0.1700
Data Index: 1610119 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0392. Min Act: -0.1700
Data Index: 5303705 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0392. Min Act: -0.1700
Data Index: 5085950 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0392. Min Act: -0.1700
Data Index: 4678296 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4142. Min Range: -5.4142
Max Act: 5.0392. Min Act: -0.1700
Data Index: 4190883 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19