Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2294 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.9454. Min Act: -0.1700
Data Index: 962537 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.8829. Min Act: -0.1700
Data Index: 5132091 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.8517. Min Act: -0.1700
Data Index: 856968 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.8204. Min Act: -0.1700
Data Index: 609332 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.7892. Min Act: -0.1700
Data Index: 962539 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.7267. Min Act: -0.1699
Data Index: 962538 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.6329. Min Act: -0.1700
Data Index: 811770 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 2660420 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.5079. Min Act: -0.1700
Data Index: 4568907 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.4767. Min Act: -0.1700
Data Index: 4568254 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.3829. Min Act: -0.1700
Data Index: 7598578 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.3204. Min Act: -0.1700
Data Index: 8806088 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.3517. Min Act: -0.1700
Data Index: 4540678 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.2892. Min Act: -0.1700
Data Index: 8151763 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.3204. Min Act: -0.1700
Data Index: 900188 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.3204. Min Act: -0.1700
Data Index: 4013831 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.3204. Min Act: -0.1700
Data Index: 841281 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.3204. Min Act: -0.1700
Data Index: 4878835 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.2892. Min Act: -0.1700
Data Index: 3056235 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9454. Min Range: -5.9454
Max Act: 5.2892. Min Act: -0.1700
Data Index: 4540677 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19