Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4383 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.8497. Min Act: -0.1700
Data Index: 8729343 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.8184. Min Act: -0.1700
Data Index: 3651563 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.8184. Min Act: -0.1700
Data Index: 5189269 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7559. Min Act: -0.1700
Data Index: 5171984 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7559. Min Act: -0.1700
Data Index: 8642164 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7559. Min Act: -0.1700
Data Index: 5522728 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7559. Min Act: -0.1700
Data Index: 2325774 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7246. Min Act: -0.1700
Data Index: 1100219 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7246. Min Act: -0.1700
Data Index: 6165165 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7246. Min Act: -0.1700
Data Index: 5485841 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7246. Min Act: -0.1700
Data Index: 4638209 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7246. Min Act: -0.1700
Data Index: 8550223 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.7246. Min Act: -0.1700
Data Index: 1954090 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.6933. Min Act: -0.1700
Data Index: 4030425 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.6933. Min Act: -0.1700
Data Index: 871588 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.6933. Min Act: -0.1700
Data Index: 785324 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.6933. Min Act: -0.1700
Data Index: 3027767 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.6933. Min Act: -0.1700
Data Index: 1727531 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.6620. Min Act: -0.1700
Data Index: 3271063 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8497. Min Range: -3.8497
Max Act: 3.6620. Min Act: -0.1700
Data Index: 5833534 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19