Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2194 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.5748. Min Act: -0.1700
Data Index: 3596022 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.5748. Min Act: -0.1700
Data Index: 4013581 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.5122. Min Act: -0.1700
Data Index: 2960391 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4965. Min Act: -0.1700
Data Index: 8005220 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4809. Min Act: -0.1700
Data Index: 2697602 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4809. Min Act: -0.1700
Data Index: 7073371 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4965. Min Act: -0.1700
Data Index: 7610034 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4652. Min Act: -0.1700
Data Index: 52420 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4809. Min Act: -0.1700
Data Index: 3708031 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4809. Min Act: -0.1700
Data Index: 2161498 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4495. Min Act: -0.1700
Data Index: 6132258 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4652. Min Act: -0.1700
Data Index: 1701128 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4809. Min Act: -0.1700
Data Index: 6610405 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4495. Min Act: -0.1700
Data Index: 8343816 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4495. Min Act: -0.1700
Data Index: 3613851 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4339. Min Act: -0.1700
Data Index: 3229463 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4652. Min Act: -0.1700
Data Index: 3343641 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4652. Min Act: -0.1700
Data Index: 2807113 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4495. Min Act: -0.1700
Data Index: 1806623 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5748. Min Range: -3.5748
Max Act: 3.4025. Min Act: -0.1700
Data Index: 4543879 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19