Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4218 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0003. Min Range: -4.0003
Max Act: 4.0003. Min Act: -0.1700
Data Index: 6236578 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.9378. Min Act: -0.1700
Data Index: 3612417 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.8127. Min Act: -0.1700
Data Index: 8604249 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.8127. Min Act: -0.1700
Data Index: 7522592 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.7814. Min Act: -0.1700
Data Index: 597149 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.7502. Min Act: -0.1700
Data Index: 3238710 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6876. Min Act: -0.1700
Data Index: 8125676 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6876. Min Act: -0.1700
Data Index: 7954959 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6876. Min Act: -0.1700
Data Index: 597143 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6876. Min Act: -0.1700
Data Index: 1077153 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6563. Min Act: -0.1700
Data Index: 331692 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6563. Min Act: -0.1700
Data Index: 5671161 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6563. Min Act: -0.1700
Data Index: 1253475 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6250. Min Act: -0.1700
Data Index: 5926053 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6250. Min Act: -0.1700
Data Index: 7292192 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.6250. Min Act: -0.1700
Data Index: 354015 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.5937. Min Act: -0.1700
Data Index: 1765596 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.5937. Min Act: -0.1700
Data Index: 7068954 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.5937. Min Act: -0.1700
Data Index: 2003143 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0003. Min Range: -4.0003
Max Act: 3.5624. Min Act: -0.1700
Data Index: 1724663 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19