Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2334 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.8144. Min Act: -0.1700
Data Index: 1469354 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.7518. Min Act: -0.1700
Data Index: 5153517 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.7518. Min Act: -0.1700
Data Index: 5105852 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.6580. Min Act: -0.1700
Data Index: 5044475 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.6267. Min Act: -0.1700
Data Index: 2871452 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.6267. Min Act: -0.1700
Data Index: 8406095 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5954. Min Act: -0.1700
Data Index: 4162806 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5954. Min Act: -0.1700
Data Index: 5517852 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5954. Min Act: -0.1700
Data Index: 3818283 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5641. Min Act: -0.1700
Data Index: 7098439 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5641. Min Act: -0.1700
Data Index: 3794931 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5641. Min Act: -0.1700
Data Index: 423231 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5954. Min Act: -0.1700
Data Index: 2112447 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5328. Min Act: -0.1700
Data Index: 3309584 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5328. Min Act: -0.1700
Data Index: 2301069 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5328. Min Act: -0.1700
Data Index: 4970040 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5328. Min Act: -0.1700
Data Index: 5035562 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5328. Min Act: -0.1700
Data Index: 3694771 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5328. Min Act: -0.1700
Data Index: 5150155 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8144. Min Range: -3.8144
Max Act: 3.5328. Min Act: -0.1700
Data Index: 1774072 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19