Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1615 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.7941. Min Act: -0.1700
Data Index: 1187122 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.7316. Min Act: -0.1700
Data Index: 4978878 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.7628. Min Act: -0.1700
Data Index: 4029297 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.5753. Min Act: -0.1700
Data Index: 7089825 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.5753. Min Act: -0.1700
Data Index: 1563159 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.5753. Min Act: -0.1700
Data Index: 2621407 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.5128. Min Act: -0.1700
Data Index: 2902710 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.4503. Min Act: -0.1700
Data Index: 7703256 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.4816. Min Act: -0.1700
Data Index: 7401577 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.4503. Min Act: -0.1700
Data Index: 7898048 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.4503. Min Act: -0.1700
Data Index: 1961394 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.4191. Min Act: -0.1700
Data Index: 802335 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.4191. Min Act: -0.1700
Data Index: 4373298 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.3878. Min Act: -0.1700
Data Index: 623502 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.3878. Min Act: -0.1700
Data Index: 3429917 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.3253. Min Act: -0.1700
Data Index: 2229485 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.2941. Min Act: -0.1700
Data Index: 2920028 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 422618 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 6240505 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7941. Min Range: -6.7941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 4925535 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19