Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.5004. Min Act: -0.1700
Data Index: 261104 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.4379. Min Act: -0.1700
Data Index: 3501811 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.4067. Min Act: -0.1700
Data Index: 7094383 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.3754. Min Act: -0.1700
Data Index: 5297350 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.2504. Min Act: -0.1700
Data Index: 4610237 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.1567. Min Act: -0.1700
Data Index: 6744993 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.1254. Min Act: -0.1700
Data Index: 1859989 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.1254. Min Act: -0.1700
Data Index: 6006994 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.0942. Min Act: -0.1700
Data Index: 7205423 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.0942. Min Act: -0.1700
Data Index: 7773018 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.0004. Min Act: -0.1700
Data Index: 4219133 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.0004. Min Act: -0.1700
Data Index: 6380793 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5004. Min Range: -5.5004
Max Act: 5.0004. Min Act: -0.1700
Data Index: 6670920 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5004. Min Range: -5.5004
Max Act: 4.9692. Min Act: -0.1700
Data Index: 4804700 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5004. Min Range: -5.5004
Max Act: 4.9379. Min Act: -0.1700
Data Index: 5101931 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5004. Min Range: -5.5004
Max Act: 4.9379. Min Act: -0.1700
Data Index: 8624880 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5004. Min Range: -5.5004
Max Act: 4.9067. Min Act: -0.1700
Data Index: 6169952 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5004. Min Range: -5.5004
Max Act: 4.8754. Min Act: -0.1700
Data Index: 3309530 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5004. Min Range: -5.5004
Max Act: 4.8754. Min Act: -0.1700
Data Index: 2971114 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5004. Min Range: -5.5004
Max Act: 4.8754. Min Act: -0.1700
Data Index: 4109929 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19