Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2389 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.9280. Min Act: -0.1700
Data Index: 4968520 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.8030. Min Act: -0.1700
Data Index: 6709923 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.6780. Min Act: -0.1700
Data Index: 7154692 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.5530. Min Act: -0.1700
Data Index: 6405810 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.3655. Min Act: -0.1700
Data Index: 7669502 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.3655. Min Act: -0.1700
Data Index: 7669501 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.3030. Min Act: -0.1700
Data Index: 3517429 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.2718. Min Act: -0.1700
Data Index: 1560407 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.3030. Min Act: -0.1700
Data Index: 7827759 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.2718. Min Act: -0.1700
Data Index: 224328 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.2093. Min Act: -0.1700
Data Index: 6775270 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.2405. Min Act: -0.1700
Data Index: 8123608 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.2093. Min Act: -0.1700
Data Index: 6077867 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.1780. Min Act: -0.1700
Data Index: 4065138 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.1780. Min Act: -0.1700
Data Index: 6758834 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.1468. Min Act: -0.1700
Data Index: 1701121 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.1468. Min Act: -0.1700
Data Index: 6437331 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.1468. Min Act: -0.1700
Data Index: 38355 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.0843. Min Act: -0.1700
Data Index: 1521992 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9280. Min Range: -7.9280
Max Act: 7.0530. Min Act: -0.1700
Data Index: 4657759 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19