Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2482 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.4149. Min Act: -0.1700
Data Index: 3945906 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.3524. Min Act: -0.1700
Data Index: 2521360 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.3212. Min Act: -0.1700
Data Index: 3306829 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.3212. Min Act: -0.1700
Data Index: 223855 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2899. Min Act: -0.1700
Data Index: 2692554 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2899. Min Act: -0.1700
Data Index: 5686936 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2899. Min Act: -0.1700
Data Index: 6870133 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2899. Min Act: -0.1700
Data Index: 726998 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 295271 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 1168323 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 6588149 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 5995226 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 6777879 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 4577211 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 4904821 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 2843085 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 5153961 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 3289072 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 6935379 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4149. Min Range: -4.4149
Max Act: 4.2587. Min Act: -0.1700
Data Index: 2460098 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19