Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.8261. Min Act: -0.1700
Data Index: 2745433 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.4823. Min Act: -0.1700
Data Index: 1697334 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.3886. Min Act: -0.1700
Data Index: 1290259 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.3261. Min Act: -0.1700
Data Index: 3045416 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.3261. Min Act: -0.1700
Data Index: 7456275 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2948. Min Act: -0.1700
Data Index: 4449697 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2636. Min Act: -0.1700
Data Index: 1205821 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2636. Min Act: -0.1700
Data Index: 7212412 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2636. Min Act: -0.1700
Data Index: 2282770 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2323. Min Act: -0.1700
Data Index: 6718553 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2323. Min Act: -0.1700
Data Index: 7404325 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2323. Min Act: -0.1700
Data Index: 3434093 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2323. Min Act: -0.1700
Data Index: 7736451 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2011. Min Act: -0.1700
Data Index: 3318138 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2011. Min Act: -0.1700
Data Index: 6462968 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2011. Min Act: -0.1700
Data Index: 7017428 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2011. Min Act: -0.1700
Data Index: 5568366 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2011. Min Act: -0.1700
Data Index: 1029295 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2011. Min Act: -0.1700
Data Index: 430995 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8261. Min Range: -5.8261
Max Act: 5.2011. Min Act: -0.1700
Data Index: 3973886 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19