Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 578 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.9741. Min Act: -0.1700
Data Index: 1073322 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.9429. Min Act: -0.1700
Data Index: 5353376 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.9116. Min Act: -0.1700
Data Index: 565309 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.8491. Min Act: -0.1700
Data Index: 41101 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.8804. Min Act: -0.1700
Data Index: 3155245 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.8179. Min Act: -0.1700
Data Index: 4692166 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.8179. Min Act: -0.1700
Data Index: 3300236 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.7866. Min Act: -0.1700
Data Index: 1442498 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.7241. Min Act: -0.1700
Data Index: 8383096 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.7554. Min Act: -0.1700
Data Index: 1386682 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.7554. Min Act: -0.1700
Data Index: 3953932 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.7241. Min Act: -0.1700
Data Index: 5992325 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.7241. Min Act: -0.1700
Data Index: 2511167 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.7241. Min Act: -0.1700
Data Index: 5443421 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.6929. Min Act: -0.1700
Data Index: 4313728 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.6929. Min Act: -0.1700
Data Index: 2012565 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.6616. Min Act: -0.1700
Data Index: 1558902 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.5991. Min Act: -0.1700
Data Index: 2012591 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.6304. Min Act: -0.1700
Data Index: 1073324 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9741. Min Range: -5.9741
Max Act: 5.5991. Min Act: -0.1700
Data Index: 1073328 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19