Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2523 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2161. Min Range: -6.2161
Max Act: 6.2161. Min Act: -0.1700
Data Index: 1489240 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9973. Min Act: -0.1700
Data Index: 1554763 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.9973. Min Act: -0.1700
Data Index: 3616175 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.8723. Min Act: -0.1700
Data Index: 840942 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.8098. Min Act: -0.1700
Data Index: 5246100 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.7786. Min Act: -0.1700
Data Index: 4770333 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.8098. Min Act: -0.1700
Data Index: 8304710 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.7786. Min Act: -0.1700
Data Index: 3987099 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.7161. Min Act: -0.1700
Data Index: 2611377 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.6848. Min Act: -0.1700
Data Index: 6447748 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.6848. Min Act: -0.1700
Data Index: 7145130 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.6223. Min Act: -0.1700
Data Index: 218360 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.6223. Min Act: -0.1700
Data Index: 6962499 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.5911. Min Act: -0.1700
Data Index: 498055 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.5598. Min Act: -0.1700
Data Index: 3389150 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.5911. Min Act: -0.1700
Data Index: 4717681 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.5598. Min Act: -0.1700
Data Index: 610968 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.5911. Min Act: -0.1700
Data Index: 280225 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.5598. Min Act: -0.1700
Data Index: 586197 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2161. Min Range: -6.2161
Max Act: 5.5598. Min Act: -0.1700
Data Index: 3091832 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19