Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.8356. Min Act: -0.1700
Data Index: 5154810 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.7418. Min Act: -0.1700
Data Index: 3091325 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.6793. Min Act: -0.1700
Data Index: 2985002 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.5856. Min Act: -0.1700
Data Index: 493983 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.4606. Min Act: -0.1700
Data Index: 4770130 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.4606. Min Act: -0.1700
Data Index: 6114800 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.4293. Min Act: -0.1700
Data Index: 7020846 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.4293. Min Act: -0.1700
Data Index: 8743992 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.3668. Min Act: -0.1700
Data Index: 8567046 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.3356. Min Act: -0.1700
Data Index: 7957421 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.3668. Min Act: -0.1700
Data Index: 5286592 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.3356. Min Act: -0.1700
Data Index: 3905956 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.2731. Min Act: -0.1700
Data Index: 2956497 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.2731. Min Act: -0.1700
Data Index: 1691565 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.3043. Min Act: -0.1700
Data Index: 1688552 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.3043. Min Act: -0.1700
Data Index: 6841882 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.2731. Min Act: -0.1700
Data Index: 3005786 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.3043. Min Act: -0.1700
Data Index: 8097536 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.2418. Min Act: -0.1700
Data Index: 7195366 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8356. Min Range: -6.8356
Max Act: 6.2418. Min Act: -0.1700
Data Index: 5192634 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19