Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1443 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.4172. Min Act: -0.1700
Data Index: 1328669 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.3547. Min Act: -0.1693
Data Index: 8614346 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.2922. Min Act: -0.1700
Data Index: 1024068 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.2922. Min Act: -0.1700
Data Index: 2502773 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.2922. Min Act: -0.1700
Data Index: 5194283 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.2297. Min Act: -0.1700
Data Index: 5264312 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1672. Min Act: -0.1700
Data Index: 3351433 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1672. Min Act: -0.1700
Data Index: 2033850 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1672. Min Act: -0.1697
Data Index: 5845298 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1672. Min Act: -0.1700
Data Index: 4574453 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1672. Min Act: -0.1700
Data Index: 2861584 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1672. Min Act: -0.1700
Data Index: 3343099 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1047. Min Act: -0.1695
Data Index: 5246775 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1047. Min Act: -0.1700
Data Index: 2117742 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1047. Min Act: -0.1700
Data Index: 8184454 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1047. Min Act: -0.1700
Data Index: 2998036 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.1672. Min Act: -0.1697
Data Index: 3209056 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4172. Min Range: -8.4172
Max Act: 7.9797. Min Act: -0.1700
Data Index: 7897119 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.0422. Min Act: -0.1700
Data Index: 7593880 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4172. Min Range: -8.4172
Max Act: 8.0422. Min Act: -0.1700
Data Index: 5323273 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19