Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 417 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.9615. Min Act: -0.1700
Data Index: 1757139 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.8365. Min Act: -0.1700
Data Index: 6099568 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.7428. Min Act: -0.1700
Data Index: 994360 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.7115. Min Act: -0.1700
Data Index: 3202118 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.6803. Min Act: -0.1700
Data Index: 3878878 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.6803. Min Act: -0.1700
Data Index: 8638592 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.6803. Min Act: -0.1700
Data Index: 4994813 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.7115. Min Act: -0.1700
Data Index: 34285 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.7115. Min Act: -0.1700
Data Index: 685795 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.5865. Min Act: -0.1700
Data Index: 7151325 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.5865. Min Act: -0.1700
Data Index: 5744615 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.6178. Min Act: -0.1700
Data Index: 4380343 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.6178. Min Act: -0.1700
Data Index: 6062905 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.5865. Min Act: -0.1700
Data Index: 5554308 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.6178. Min Act: -0.1700
Data Index: 3835570 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.5865. Min Act: -0.1700
Data Index: 4177351 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.5553. Min Act: -0.1700
Data Index: 1652620 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.5553. Min Act: -0.1700
Data Index: 5964346 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.5553. Min Act: -0.1700
Data Index: 5146638 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9615. Min Range: -6.9615
Max Act: 6.4928. Min Act: -0.1700
Data Index: 2558833 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19