Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.7115. Min Act: -0.1700
Data Index: 3848083 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7115. Min Range: -8.7115
Max Act: 8.0240. Min Act: -0.1700
Data Index: 3016218 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.9615. Min Act: -0.1700
Data Index: 90077 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.8990. Min Act: -0.1700
Data Index: 430391 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.8365. Min Act: -0.1700
Data Index: 3347988 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.7115. Min Act: -0.1700
Data Index: 2603704 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.7115. Min Act: -0.1700
Data Index: 8269849 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.6490. Min Act: -0.1700
Data Index: 6000196 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.7115. Min Act: -0.1700
Data Index: 1410140 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.7115. Min Act: -0.1700
Data Index: 964762 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.5865. Min Act: -0.1700
Data Index: 5768308 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.5552. Min Act: -0.1700
Data Index: 50182 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.5552. Min Act: -0.1700
Data Index: 4513068 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.5240. Min Act: -0.1700
Data Index: 5685008 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.5552. Min Act: -0.1700
Data Index: 1083631 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.5240. Min Act: -0.1700
Data Index: 7599834 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.5240. Min Act: -0.1700
Data Index: 568355 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.4927. Min Act: -0.1700
Data Index: 447014 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.4927. Min Act: -0.1700
Data Index: 6261024 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7115. Min Range: -8.7115
Max Act: 7.5240. Min Act: -0.1700
Data Index: 7275472 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19