Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4350 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0456. Min Range: -10.0456
Max Act: 10.0456. Min Act: -0.1700
Data Index: 1261630 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.7956. Min Act: -0.1700
Data Index: 5755946 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.7331. Min Act: -0.1700
Data Index: 7511501 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.6706. Min Act: -0.1700
Data Index: 4875097 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.6081. Min Act: -0.1700
Data Index: 3116019 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.4831. Min Act: -0.1700
Data Index: 6823844 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.4831. Min Act: -0.1700
Data Index: 2803257 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.5456. Min Act: -0.1700
Data Index: 693576 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.4206. Min Act: -0.1700
Data Index: 2817311 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.4206. Min Act: -0.1700
Data Index: 1137012 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.3581. Min Act: -0.1700
Data Index: 2616717 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.3581. Min Act: -0.1700
Data Index: 1240433 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.2956. Min Act: -0.1700
Data Index: 8778464 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.2331. Min Act: -0.1700
Data Index: 2294025 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.2956. Min Act: -0.1700
Data Index: 4807616 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.2956. Min Act: -0.1700
Data Index: 6082376 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.2956. Min Act: -0.1700
Data Index: 6722164 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.2331. Min Act: -0.1700
Data Index: 3599400 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.2331. Min Act: -0.1700
Data Index: 7811790 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0456. Min Range: -10.0456
Max Act: 9.2331. Min Act: -0.1700
Data Index: 4476869 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19