Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 262 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.7868. Min Act: -0.1700
Data Index: 8831536 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.7555. Min Act: -0.1700
Data Index: 6480026 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.7243. Min Act: -0.1700
Data Index: 5699288 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.7243. Min Act: -0.1700
Data Index: 1672085 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.6930. Min Act: -0.1700
Data Index: 8748226 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.7243. Min Act: -0.1700
Data Index: 6687739 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.5368. Min Act: -0.1700
Data Index: 5620424 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.5368. Min Act: -0.1700
Data Index: 2856226 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.5055. Min Act: -0.1700
Data Index: 2253397 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.5055. Min Act: -0.1700
Data Index: 6284836 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.5368. Min Act: -0.1700
Data Index: 521328 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.5055. Min Act: -0.1700
Data Index: 602288 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.5368. Min Act: -0.1700
Data Index: 8634190 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.5368. Min Act: -0.1700
Data Index: 966032 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.4743. Min Act: -0.1700
Data Index: 2988173 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.4743. Min Act: -0.1700
Data Index: 5409371 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.4743. Min Act: -0.1700
Data Index: 7197838 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.4743. Min Act: -0.1700
Data Index: 1885429 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.4118. Min Act: -0.1700
Data Index: 4115032 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.4430. Min Act: -0.1700
Data Index: 1576472 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19