Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.6107. Min Act: -0.1700
Data Index: 6592512 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.6107. Min Act: -0.1700
Data Index: 5396078 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.4857. Min Act: -0.1700
Data Index: 2736694 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.4232. Min Act: -0.1700
Data Index: 4683172 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.3607. Min Act: -0.1700
Data Index: 1938266 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.2669. Min Act: -0.1700
Data Index: 1857222 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.2669. Min Act: -0.1700
Data Index: 441493 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.2044. Min Act: -0.1700
Data Index: 6514671 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.2044. Min Act: -0.1700
Data Index: 5631531 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.1732. Min Act: -0.1700
Data Index: 7464643 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.0794. Min Act: -0.1700
Data Index: 5335646 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.1107. Min Act: -0.1700
Data Index: 2480937 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.1107. Min Act: -0.1700
Data Index: 2576618 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.1107. Min Act: -0.1700
Data Index: 7410288 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.0482. Min Act: -0.1700
Data Index: 5216260 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6107. Min Range: -8.6107
Max Act: 8.0169. Min Act: -0.1700
Data Index: 3421839 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6107. Min Range: -8.6107
Max Act: 7.9544. Min Act: -0.1700
Data Index: 55186 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6107. Min Range: -8.6107
Max Act: 7.9232. Min Act: -0.1700
Data Index: 3168054 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6107. Min Range: -8.6107
Max Act: 7.8607. Min Act: -0.1700
Data Index: 5780393 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6107. Min Range: -8.6107
Max Act: 7.8294. Min Act: -0.1700
Data Index: 1001336 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19