Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0411. Min Range: -6.0411
Max Act: 6.0411. Min Act: -0.1700
Data Index: 2510567 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0411. Min Range: -6.0411
Max Act: 6.0411. Min Act: -0.1700
Data Index: 1654292 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0411. Min Range: -6.0411
Max Act: 6.0099. Min Act: -0.1700
Data Index: 1518156 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.9474. Min Act: -0.1700
Data Index: 6317835 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.9161. Min Act: -0.1700
Data Index: 4850398 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.8536. Min Act: -0.1700
Data Index: 4672036 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.8849. Min Act: -0.1700
Data Index: 7313393 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.8536. Min Act: -0.1700
Data Index: 1226214 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.8536. Min Act: -0.1700
Data Index: 8272578 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.8224. Min Act: -0.1700
Data Index: 8182341 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.8224. Min Act: -0.1700
Data Index: 2966050 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7911. Min Act: -0.1700
Data Index: 485551 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7911. Min Act: -0.1700
Data Index: 2645089 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7599. Min Act: -0.1700
Data Index: 337419 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7599. Min Act: -0.1700
Data Index: 930018 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7286. Min Act: -0.1700
Data Index: 6376743 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7599. Min Act: -0.1700
Data Index: 5231514 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7599. Min Act: -0.1700
Data Index: 5791174 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7286. Min Act: -0.1700
Data Index: 6635839 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0411. Min Range: -6.0411
Max Act: 5.7286. Min Act: -0.1700
Data Index: 4510841 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19