Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3570 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.7270. Min Act: -0.1700
Data Index: 7792572 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.5083. Min Act: -0.1700
Data Index: 7201077 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.5083. Min Act: -0.1700
Data Index: 4671157 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.5083. Min Act: -0.1700
Data Index: 882072 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.4770. Min Act: -0.1700
Data Index: 7662725 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.4770. Min Act: -0.1700
Data Index: 6932017 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.4458. Min Act: -0.1700
Data Index: 586321 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.4145. Min Act: -0.1700
Data Index: 3722078 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.3833. Min Act: -0.1700
Data Index: 4790920 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.3520. Min Act: -0.1700
Data Index: 43013 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.3833. Min Act: -0.1700
Data Index: 1777096 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.3833. Min Act: -0.1700
Data Index: 5492078 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.2895. Min Act: -0.1700
Data Index: 1138498 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.3208. Min Act: -0.1700
Data Index: 7192784 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.3208. Min Act: -0.1700
Data Index: 8117638 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.3208. Min Act: -0.1700
Data Index: 3177996 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.2895. Min Act: -0.1700
Data Index: 1313995 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.2895. Min Act: -0.1700
Data Index: 830710 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.2895. Min Act: -0.1700
Data Index: 5536316 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7270. Min Range: -5.7270
Max Act: 5.2895. Min Act: -0.1700
Data Index: 6503256 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19