Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2145 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.8295. Min Act: -0.1700
Data Index: 7246988 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.7779. Min Act: -0.1700
Data Index: 5564018 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.7261. Min Act: -0.1700
Data Index: 8020767 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.7261. Min Act: -0.1700
Data Index: 5835006 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6740. Min Act: -0.1700
Data Index: 3720001 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6740. Min Act: -0.1700
Data Index: 7551060 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6740. Min Act: -0.1700
Data Index: 4215196 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6567. Min Act: -0.1700
Data Index: 662056 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6567. Min Act: -0.1700
Data Index: 5197527 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6567. Min Act: -0.1700
Data Index: 5595104 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6392. Min Act: -0.1700
Data Index: 6963395 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6567. Min Act: -0.1700
Data Index: 1040199 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6392. Min Act: -0.1700
Data Index: 6306108 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6392. Min Act: -0.1700
Data Index: 6238693 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6218. Min Act: -0.1700
Data Index: 1024003 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6218. Min Act: -0.1700
Data Index: 8437314 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6392. Min Act: -0.1700
Data Index: 4453176 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6044. Min Act: -0.1700
Data Index: 7589214 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6044. Min Act: -0.1700
Data Index: 4933480 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8295. Min Range: -1.8295
Max Act: 1.6044. Min Act: -0.1700
Data Index: 5331137 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19