Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1574 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2449. Min Range: -7.2449
Max Act: 7.2449. Min Act: -0.1700
Data Index: 798431 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2449. Min Range: -7.2449
Max Act: 7.1512. Min Act: -0.1700
Data Index: 4555670 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2449. Min Range: -7.2449
Max Act: 7.1512. Min Act: -0.1700
Data Index: 1713904 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2449. Min Range: -7.2449
Max Act: 7.1824. Min Act: -0.1700
Data Index: 6697429 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2449. Min Range: -7.2449
Max Act: 7.1199. Min Act: -0.1700
Data Index: 4192567 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2449. Min Range: -7.2449
Max Act: 7.0262. Min Act: -0.1700
Data Index: 8449231 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.9324. Min Act: -0.1700
Data Index: 26562 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.9012. Min Act: -0.1700
Data Index: 3371917 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.9012. Min Act: -0.1700
Data Index: 1177825 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8387. Min Act: -0.1700
Data Index: 995326 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8699. Min Act: -0.1700
Data Index: 5525187 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8387. Min Act: -0.1700
Data Index: 2779612 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8699. Min Act: -0.1700
Data Index: 224396 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8387. Min Act: -0.1700
Data Index: 1355174 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8387. Min Act: -0.1700
Data Index: 2185392 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8387. Min Act: -0.1700
Data Index: 7013659 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8074. Min Act: -0.1700
Data Index: 5812435 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8074. Min Act: -0.1700
Data Index: 1356027 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8074. Min Act: -0.1700
Data Index: 1366399 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2449. Min Range: -7.2449
Max Act: 6.8074. Min Act: -0.1700
Data Index: 4072423 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19