Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.7148. Min Act: -0.1700
Data Index: 5413313 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.7148. Min Act: -0.1700
Data Index: 7591422 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.6835. Min Act: -0.1700
Data Index: 4866715 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.6523. Min Act: -0.1700
Data Index: 1453145 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.6210. Min Act: -0.1700
Data Index: 2313249 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5898. Min Act: -0.1700
Data Index: 8220493 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5898. Min Act: -0.1700
Data Index: 5997500 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5898. Min Act: -0.1700
Data Index: 1991325 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5898. Min Act: -0.1700
Data Index: 7315517 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5898. Min Act: -0.1700
Data Index: 7896765 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5585. Min Act: -0.1700
Data Index: 8411065 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5585. Min Act: -0.1700
Data Index: 2996638 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.4960. Min Act: -0.1700
Data Index: 6666434 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.4960. Min Act: -0.1700
Data Index: 3406250 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5273. Min Act: -0.1700
Data Index: 4069819 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5273. Min Act: -0.1700
Data Index: 5709812 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.5273. Min Act: -0.1700
Data Index: 4427691 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.4960. Min Act: -0.1700
Data Index: 4063204 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.4648. Min Act: -0.1700
Data Index: 6857250 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7148. Min Range: -4.7148
Max Act: 4.4960. Min Act: -0.1700
Data Index: 520479 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19