Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2365 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.6830. Min Act: -0.1700
Data Index: 7094813 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.6517. Min Act: -0.1700
Data Index: 7304568 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.5580. Min Act: -0.1700
Data Index: 1690792 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.5580. Min Act: -0.1700
Data Index: 2578323 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.5267. Min Act: -0.1700
Data Index: 3492365 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.5267. Min Act: -0.1700
Data Index: 1261053 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4642. Min Act: -0.1700
Data Index: 7487379 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4330. Min Act: -0.1700
Data Index: 2811136 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4330. Min Act: -0.1700
Data Index: 5028087 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4330. Min Act: -0.1700
Data Index: 5843151 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4017. Min Act: -0.1700
Data Index: 5823307 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4330. Min Act: -0.1700
Data Index: 5481407 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3705. Min Act: -0.1700
Data Index: 1296631 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3705. Min Act: -0.1700
Data Index: 7586543 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3705. Min Act: -0.1700
Data Index: 3745511 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3392. Min Act: -0.1700
Data Index: 4460442 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3080. Min Act: -0.1700
Data Index: 3722338 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3392. Min Act: -0.1700
Data Index: 3662783 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3392. Min Act: -0.1700
Data Index: 53229 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3392. Min Act: -0.1700
Data Index: 5201314 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19