Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 945 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2648. Min Range: -3.2648
Max Act: 3.2648. Min Act: -0.1700
Data Index: 5678835 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2648. Min Range: -3.2648
Max Act: 3.1390. Min Act: -0.1700
Data Index: 6587711 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2648. Min Range: -3.2648
Max Act: 3.0444. Min Act: -0.1700
Data Index: 5678836 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2648. Min Range: -3.2648
Max Act: 3.0444. Min Act: -0.1700
Data Index: 6850870 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9970. Min Act: -0.1700
Data Index: 8213177 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9970. Min Act: -0.1700
Data Index: 4400547 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9812. Min Act: -0.1700
Data Index: 442889 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9495. Min Act: -0.1700
Data Index: 4853449 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9337. Min Act: -0.1700
Data Index: 6297628 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9337. Min Act: -0.1700
Data Index: 4876500 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9495. Min Act: -0.1700
Data Index: 4757709 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9179. Min Act: -0.1700
Data Index: 2437220 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9179. Min Act: -0.1700
Data Index: 7073025 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9020. Min Act: -0.1700
Data Index: 7809244 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9020. Min Act: -0.1700
Data Index: 6603162 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9179. Min Act: -0.1700
Data Index: 4077876 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.8861. Min Act: -0.1700
Data Index: 7310433 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.8861. Min Act: -0.1700
Data Index: 3388187 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.8861. Min Act: -0.1700
Data Index: 8786130 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2648. Min Range: -3.2648
Max Act: 2.9020. Min Act: -0.1700
Data Index: 4856624 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19