Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.9042. Min Act: -0.1700
Data Index: 8752358 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8872. Min Act: -0.1700
Data Index: 5650816 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.9042. Min Act: -0.1700
Data Index: 2609415 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8872. Min Act: -0.1700
Data Index: 695342 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8701. Min Act: -0.1700
Data Index: 1702873 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8530. Min Act: -0.1700
Data Index: 8599468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8530. Min Act: -0.1698
Data Index: 5357403 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8701. Min Act: -0.1700
Data Index: 2501675 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8530. Min Act: -0.1700
Data Index: 2059046 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8530. Min Act: -0.1700
Data Index: 7139762 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8444. Min Act: -0.1700
Data Index: 235594 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8444. Min Act: -0.1700
Data Index: 2585430 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8444. Min Act: -0.1700
Data Index: 5133048 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8358. Min Act: -0.1700
Data Index: 28923 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8358. Min Act: -0.1700
Data Index: 8433514 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8358. Min Act: -0.1700
Data Index: 2725495 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8187. Min Act: -0.1699
Data Index: 8671860 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8272. Min Act: -0.1700
Data Index: 5374818 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8358. Min Act: -0.1700
Data Index: 2804781 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9042. Min Range: -1.9042
Max Act: 1.8187. Min Act: -0.1700
Data Index: 4089317 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19