Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3706 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4902. Min Act: -0.1700
Data Index: 5643957 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4589. Min Act: -0.1700
Data Index: 4913342 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4277. Min Act: -0.1700
Data Index: 489004 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4277. Min Act: -0.1700
Data Index: 8829373 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.4277. Min Act: -0.1700
Data Index: 1712189 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3652. Min Act: -0.1700
Data Index: 2138931 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3027. Min Act: -0.1700
Data Index: 4492023 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.3027. Min Act: -0.1700
Data Index: 1758199 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2714. Min Act: -0.1700
Data Index: 8803017 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2714. Min Act: -0.1700
Data Index: 2680596 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2714. Min Act: -0.1700
Data Index: 2450094 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2714. Min Act: -0.1700
Data Index: 7920921 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2402. Min Act: -0.1700
Data Index: 7163174 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2089. Min Act: -0.1700
Data Index: 7465211 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2089. Min Act: -0.1700
Data Index: 4557450 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2089. Min Act: -0.1700
Data Index: 488999 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.2089. Min Act: -0.1700
Data Index: 5253027 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.1777. Min Act: -0.1700
Data Index: 860951 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.1777. Min Act: -0.1700
Data Index: 3916739 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4902. Min Range: -5.4902
Max Act: 5.1777. Min Act: -0.1700
Data Index: 526605 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19