Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2214 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.4373. Min Act: -0.1700
Data Index: 5732876 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.3065. Min Act: -0.1700
Data Index: 2971215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.3065. Min Act: -0.1700
Data Index: 8271374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.2735. Min Act: -0.1700
Data Index: 6410205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.2570. Min Act: -0.1700
Data Index: 1938553 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1908. Min Act: -0.1700
Data Index: 2172687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1742. Min Act: -0.1700
Data Index: 1453432 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1575. Min Act: -0.1700
Data Index: 4884750 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1575. Min Act: -0.1700
Data Index: 4889719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1575. Min Act: -0.1700
Data Index: 4460453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1742. Min Act: -0.1700
Data Index: 571465 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1575. Min Act: -0.1700
Data Index: 5035355 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1575. Min Act: -0.1700
Data Index: 2287672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1575. Min Act: -0.1700
Data Index: 8454466 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1575. Min Act: -0.1700
Data Index: 1205661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1242. Min Act: -0.1700
Data Index: 6121373 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1242. Min Act: -0.1700
Data Index: 2734050 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1242. Min Act: -0.1700
Data Index: 1746460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1074. Min Act: -0.1700
Data Index: 6645442 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4373. Min Range: -2.4373
Max Act: 2.1074. Min Act: -0.1700
Data Index: 7206524 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19