Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4722 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.6074. Min Act: -0.1700
Data Index: 3092375 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.5449. Min Act: -0.1700
Data Index: 1263149 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.4199. Min Act: -0.1700
Data Index: 8214467 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.3574. Min Act: -0.1700
Data Index: 2217477 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.3261. Min Act: -0.1700
Data Index: 1957198 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2949. Min Act: -0.1700
Data Index: 3398794 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2949. Min Act: -0.1700
Data Index: 6019019 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2324. Min Act: -0.1700
Data Index: 1739465 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2011. Min Act: -0.1700
Data Index: 8652159 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2011. Min Act: -0.1700
Data Index: 5806737 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2011. Min Act: -0.1700
Data Index: 5541937 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2011. Min Act: -0.1700
Data Index: 7599808 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2011. Min Act: -0.1700
Data Index: 7119203 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.2011. Min Act: -0.1700
Data Index: 3681885 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.1386. Min Act: -0.1700
Data Index: 5753054 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.1699. Min Act: -0.1700
Data Index: 3638677 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.1699. Min Act: -0.1700
Data Index: 4033227 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.1699. Min Act: -0.1700
Data Index: 1904272 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.1386. Min Act: -0.1700
Data Index: 967639 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6074. Min Range: -5.6074
Max Act: 5.1386. Min Act: -0.1700
Data Index: 352019 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19