Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 422 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.4902. Min Act: -0.1700
Data Index: 7975990 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.4902. Min Act: -0.1700
Data Index: 1267954 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.3027. Min Act: -0.1700
Data Index: 7710944 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.3652. Min Act: -0.1700
Data Index: 1646391 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.3027. Min Act: -0.1700
Data Index: 7818058 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.2402. Min Act: -0.1700
Data Index: 7047704 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.2402. Min Act: -0.1700
Data Index: 2478335 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.2402. Min Act: -0.1700
Data Index: 2726185 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.1777. Min Act: -0.1700
Data Index: 5884814 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.1152. Min Act: -0.1700
Data Index: 1657947 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.1152. Min Act: -0.1700
Data Index: 6089679 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.1777. Min Act: -0.1700
Data Index: 1541328 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.1152. Min Act: -0.1700
Data Index: 6474949 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.0527. Min Act: -0.1700
Data Index: 5660040 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.9902. Min Act: -0.1700
Data Index: 1426662 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.0527. Min Act: -0.1700
Data Index: 5218172 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.0527. Min Act: -0.1700
Data Index: 4718524 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.0527. Min Act: -0.1700
Data Index: 1028863 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.9902. Min Act: -0.1700
Data Index: 1088834 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.9902. Min Act: -0.1700
Data Index: 1346036 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19