Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.5639. Min Act: -0.1700
Data Index: 8786352 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.5327. Min Act: -0.1700
Data Index: 6007286 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.4389. Min Act: -0.1700
Data Index: 442556 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.4389. Min Act: -0.1700
Data Index: 2476330 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.4077. Min Act: -0.1700
Data Index: 4683676 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.4077. Min Act: -0.1700
Data Index: 4706244 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.3764. Min Act: -0.1700
Data Index: 7906393 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.3452. Min Act: -0.1700
Data Index: 4623212 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.3139. Min Act: -0.1700
Data Index: 8282519 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.2827. Min Act: -0.1700
Data Index: 3842390 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.3139. Min Act: -0.1700
Data Index: 7535965 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.2514. Min Act: -0.1700
Data Index: 7659911 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.2514. Min Act: -0.1700
Data Index: 7275584 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.2514. Min Act: -0.1700
Data Index: 8647648 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.2202. Min Act: -0.1700
Data Index: 7791323 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.1889. Min Act: -0.1700
Data Index: 3205682 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.1889. Min Act: -0.1700
Data Index: 7868552 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.1577. Min Act: -0.1700
Data Index: 97321 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.1577. Min Act: -0.1700
Data Index: 6284487 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5639. Min Range: -6.5639
Max Act: 6.1577. Min Act: -0.1700
Data Index: 3530997 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19