Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3046 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.7892. Min Act: -0.1700
Data Index: 7584120 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.6642. Min Act: -0.1700
Data Index: 842533 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.6017. Min Act: -0.1700
Data Index: 6309501 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.3517. Min Act: -0.1700
Data Index: 1278094 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.4142. Min Act: -0.1700
Data Index: 842535 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.2892. Min Act: -0.1700
Data Index: 6433206 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.0392. Min Act: -0.1700
Data Index: 3418330 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.0392. Min Act: -0.1700
Data Index: 6066321 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.0392. Min Act: -0.1700
Data Index: 5006589 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.1017. Min Act: -0.1700
Data Index: 8441554 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9767. Min Act: -0.1700
Data Index: 1922367 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9767. Min Act: -0.1700
Data Index: 8596491 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9767. Min Act: -0.1700
Data Index: 2466830 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7892. Min Range: -9.7892
Max Act: 9.0392. Min Act: -0.1700
Data Index: 2189823 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9142. Min Act: -0.1700
Data Index: 7217219 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9767. Min Act: -0.1700
Data Index: 3542255 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9142. Min Act: -0.1700
Data Index: 3573264 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9142. Min Act: -0.1700
Data Index: 2228885 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9142. Min Act: -0.1700
Data Index: 132809 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7892. Min Range: -9.7892
Max Act: 8.9142. Min Act: -0.1700
Data Index: 3966135 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19