Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5273 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2320. Min Range: -8.2320
Max Act: 8.2320. Min Act: -0.1700
Data Index: 1135621 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.9820. Min Act: -0.1700
Data Index: 2267439 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.9195. Min Act: -0.1700
Data Index: 7707614 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.7320. Min Act: -0.1700
Data Index: 1233365 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.6695. Min Act: -0.1700
Data Index: 7987652 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.6070. Min Act: -0.1700
Data Index: 2335921 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.5132. Min Act: -0.1700
Data Index: 7189877 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.4195. Min Act: -0.1700
Data Index: 1659227 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.2945. Min Act: -0.1700
Data Index: 465011 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.2632. Min Act: -0.1700
Data Index: 8048286 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.2320. Min Act: -0.1700
Data Index: 3102996 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.2945. Min Act: -0.1700
Data Index: 6761832 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.2320. Min Act: -0.1700
Data Index: 4119964 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.2007. Min Act: -0.1700
Data Index: 2396408 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.0757. Min Act: -0.1700
Data Index: 883436 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.0445. Min Act: -0.1700
Data Index: 4332668 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.0445. Min Act: -0.1700
Data Index: 1585467 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.0132. Min Act: -0.1700
Data Index: 3856672 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2320. Min Range: -8.2320
Max Act: 7.0132. Min Act: -0.1700
Data Index: 883437 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2320. Min Range: -8.2320
Max Act: 6.9820. Min Act: -0.1700
Data Index: 7581308 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19