Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1295. Min Range: -10.1295
Max Act: 10.1295. Min Act: -0.1700
Data Index: 3186560 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1295. Min Range: -10.1295
Max Act: 10.0045. Min Act: -0.1700
Data Index: 1628342 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1295. Min Range: -10.1295
Max Act: 10.0045. Min Act: -0.1700
Data Index: 5990873 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1295. Min Range: -10.1295
Max Act: 10.0045. Min Act: -0.1700
Data Index: 3206437 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.8170. Min Act: -0.1700
Data Index: 3155238 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.8170. Min Act: -0.1700
Data Index: 3581421 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.8170. Min Act: -0.1700
Data Index: 4782933 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.8170. Min Act: -0.1700
Data Index: 1788489 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.8170. Min Act: -0.1700
Data Index: 6096144 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.7545. Min Act: -0.1700
Data Index: 440040 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.5045. Min Act: -0.1700
Data Index: 3847510 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.5670. Min Act: -0.1700
Data Index: 554642 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.5670. Min Act: -0.1700
Data Index: 2559113 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.5045. Min Act: -0.1700
Data Index: 7395112 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.5045. Min Act: -0.1700
Data Index: 8399961 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.5045. Min Act: -0.1700
Data Index: 6870201 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.4420. Min Act: -0.1700
Data Index: 2136381 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.4420. Min Act: -0.1700
Data Index: 4545061 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.4420. Min Act: -0.1700
Data Index: 5755238 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1295. Min Range: -10.1295
Max Act: 9.4420. Min Act: -0.1700
Data Index: 5185727 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19