Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4964. Min Act: -0.1700
Data Index: 7663324 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4700. Min Act: -0.1700
Data Index: 3478362 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4612. Min Act: -0.1700
Data Index: 3358302 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4524. Min Act: -0.1700
Data Index: 1914854 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4612. Min Act: -0.1700
Data Index: 612639 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4612. Min Act: -0.1700
Data Index: 5023705 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4349. Min Act: -0.1700
Data Index: 5880415 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4349. Min Act: -0.1698
Data Index: 4070407 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4437. Min Act: -0.1700
Data Index: 2186652 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4437. Min Act: -0.1596
Data Index: 4428625 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4260. Min Act: -0.1700
Data Index: 408299 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4172. Min Act: -0.1700
Data Index: 6298929 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4437. Min Act: -0.1700
Data Index: 579893 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4260. Min Act: -0.1700
Data Index: 6005640 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4172. Min Act: -0.1700
Data Index: 5435234 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4172. Min Act: -0.1689
Data Index: 1808216 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4172. Min Act: -0.1700
Data Index: 601065 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4084. Min Act: -0.1700
Data Index: 1196511 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4084. Min Act: -0.1695
Data Index: 263913 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4964. Min Range: -1.4964
Max Act: 1.4084. Min Act: -0.1698
Data Index: 2379405 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19