Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1457 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.8311. Min Act: -0.1700
Data Index: 8567259 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.8311. Min Act: -0.1700
Data Index: 8724557 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.7999. Min Act: -0.1700
Data Index: 1736177 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.7061. Min Act: -0.1700
Data Index: 4587014 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.7061. Min Act: -0.1700
Data Index: 6792383 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.7061. Min Act: -0.1700
Data Index: 7993922 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.6436. Min Act: -0.1700
Data Index: 5146270 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.5811. Min Act: -0.1700
Data Index: 4627067 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.6124. Min Act: -0.1700
Data Index: 1273573 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.5186. Min Act: -0.1700
Data Index: 4277825 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.5186. Min Act: -0.1700
Data Index: 7734001 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.4874. Min Act: -0.1700
Data Index: 6379589 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.4874. Min Act: -0.1700
Data Index: 8456137 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.4249. Min Act: -0.1700
Data Index: 7049793 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.4249. Min Act: -0.1700
Data Index: 2911998 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.4249. Min Act: -0.1700
Data Index: 3082248 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.3936. Min Act: -0.1700
Data Index: 4095828 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.3936. Min Act: -0.1700
Data Index: 827227 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.3936. Min Act: -0.1700
Data Index: 4992633 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8311. Min Range: -5.8311
Max Act: 5.3624. Min Act: -0.1700
Data Index: 5713402 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19