Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1439 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2961. Min Range: -6.2961
Max Act: 6.2961. Min Act: -0.1700
Data Index: 7313279 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2961. Min Range: -6.2961
Max Act: 6.0461. Min Act: -0.1700
Data Index: 1975901 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2961. Min Range: -6.2961
Max Act: 6.0461. Min Act: -0.1700
Data Index: 5222310 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2961. Min Range: -6.2961
Max Act: 6.0149. Min Act: -0.1700
Data Index: 3167706 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.9836. Min Act: -0.1700
Data Index: 816058 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.9524. Min Act: -0.1700
Data Index: 3755542 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.9524. Min Act: -0.1700
Data Index: 2156975 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.9211. Min Act: -0.1700
Data Index: 450235 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8899. Min Act: -0.1700
Data Index: 8680764 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8899. Min Act: -0.1700
Data Index: 101257 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8586. Min Act: -0.1700
Data Index: 3735899 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8586. Min Act: -0.1700
Data Index: 7278647 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8586. Min Act: -0.1700
Data Index: 8312828 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8274. Min Act: -0.1700
Data Index: 806459 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.7961. Min Act: -0.1700
Data Index: 5290447 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8274. Min Act: -0.1700
Data Index: 7196915 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8274. Min Act: -0.1700
Data Index: 6748186 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.8274. Min Act: -0.1700
Data Index: 3227356 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.7961. Min Act: -0.1700
Data Index: 2732033 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2961. Min Range: -6.2961
Max Act: 5.7961. Min Act: -0.1700
Data Index: 3761950 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19