Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.4102. Min Act: -0.1700
Data Index: 441422 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.3775. Min Act: -0.1700
Data Index: 6989277 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.3939. Min Act: -0.1700
Data Index: 7468367 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.3612. Min Act: -0.1700
Data Index: 948558 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.3284. Min Act: -0.1700
Data Index: 3107974 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.3448. Min Act: -0.1700
Data Index: 6522728 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.3120. Min Act: -0.1700
Data Index: 6411388 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2955. Min Act: -0.1700
Data Index: 324628 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2955. Min Act: -0.1700
Data Index: 4016381 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2955. Min Act: -0.1700
Data Index: 8167465 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2955. Min Act: -0.1700
Data Index: 3142794 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2791. Min Act: -0.1700
Data Index: 4156975 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2955. Min Act: -0.1700
Data Index: 764061 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2791. Min Act: -0.1700
Data Index: 5163848 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2626. Min Act: -0.1700
Data Index: 2216300 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2626. Min Act: -0.1700
Data Index: 7354525 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2626. Min Act: -0.1700
Data Index: 1803282 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2626. Min Act: -0.1700
Data Index: 5305504 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2791. Min Act: -0.1700
Data Index: 1216278 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4102. Min Range: -2.4102
Max Act: 2.2626. Min Act: -0.1700
Data Index: 2968333 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19