Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.6847. Min Act: -0.1700
Data Index: 2890288 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.5597. Min Act: -0.1700
Data Index: 1855849 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.5284. Min Act: -0.1700
Data Index: 78488 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.4347. Min Act: -0.1700
Data Index: 8609052 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.4034. Min Act: -0.1700
Data Index: 3632444 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.4034. Min Act: -0.1700
Data Index: 2340635 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.3722. Min Act: -0.1700
Data Index: 8194290 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.3409. Min Act: -0.1700
Data Index: 6442902 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.3409. Min Act: -0.1700
Data Index: 5920460 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2472. Min Act: -0.1700
Data Index: 6393160 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2784. Min Act: -0.1700
Data Index: 6908372 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2159. Min Act: -0.1700
Data Index: 3632412 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2472. Min Act: -0.1700
Data Index: 8567757 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2784. Min Act: -0.1700
Data Index: 1331653 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2472. Min Act: -0.1700
Data Index: 7362644 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2472. Min Act: -0.1700
Data Index: 4245993 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2159. Min Act: -0.1700
Data Index: 3229940 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2159. Min Act: -0.1700
Data Index: 488959 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2159. Min Act: -0.1700
Data Index: 7432341 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6847. Min Range: -4.6847
Max Act: 4.2159. Min Act: -0.1700
Data Index: 1665773 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19