Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0739. Min Range: -8.0739
Max Act: 8.0739. Min Act: -0.1700
Data Index: 5506044 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.8864. Min Act: -0.1700
Data Index: 6152286 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.8864. Min Act: -0.1700
Data Index: 8458015 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.8239. Min Act: -0.1700
Data Index: 8596263 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.6989. Min Act: -0.1700
Data Index: 8194185 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.6989. Min Act: -0.1700
Data Index: 1301391 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.6364. Min Act: -0.1700
Data Index: 6725148 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.5427. Min Act: -0.1700
Data Index: 2577556 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.5427. Min Act: -0.1700
Data Index: 2255888 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.5114. Min Act: -0.1700
Data Index: 3798182 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.5114. Min Act: -0.1700
Data Index: 7322664 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.4802. Min Act: -0.1700
Data Index: 4207127 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.4489. Min Act: -0.1700
Data Index: 4008001 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.4177. Min Act: -0.1700
Data Index: 2171392 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.4177. Min Act: -0.1700
Data Index: 7467551 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.3864. Min Act: -0.1700
Data Index: 3450475 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.4177. Min Act: -0.1700
Data Index: 4176445 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.4177. Min Act: -0.1700
Data Index: 4870038 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.4177. Min Act: -0.1700
Data Index: 4187970 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0739. Min Range: -8.0739
Max Act: 7.4177. Min Act: -0.1700
Data Index: 8508944 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19