Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.5197. Min Act: -0.1700
Data Index: 8488848 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.3635. Min Act: -0.1700
Data Index: 5522984 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.3322. Min Act: -0.1700
Data Index: 8601638 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.2697. Min Act: -0.1700
Data Index: 6013614 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.2697. Min Act: -0.1700
Data Index: 3292578 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.1760. Min Act: -0.1700
Data Index: 4294400 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.1135. Min Act: -0.1700
Data Index: 8469435 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.1135. Min Act: -0.1700
Data Index: 2783836 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.0822. Min Act: -0.1700
Data Index: 6820981 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.0510. Min Act: -0.1700
Data Index: 3356800 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.0197. Min Act: -0.1700
Data Index: 7725286 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5197. Min Range: -6.5197
Max Act: 6.0197. Min Act: -0.1700
Data Index: 6883510 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5197. Min Range: -6.5197
Max Act: 5.9885. Min Act: -0.1700
Data Index: 1847290 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5197. Min Range: -6.5197
Max Act: 5.9885. Min Act: -0.1700
Data Index: 2631909 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5197. Min Range: -6.5197
Max Act: 5.9885. Min Act: -0.1700
Data Index: 8200775 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5197. Min Range: -6.5197
Max Act: 5.9572. Min Act: -0.1700
Data Index: 5514790 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5197. Min Range: -6.5197
Max Act: 5.9572. Min Act: -0.1700
Data Index: 2686026 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5197. Min Range: -6.5197
Max Act: 5.9572. Min Act: -0.1700
Data Index: 5068985 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5197. Min Range: -6.5197
Max Act: 5.9572. Min Act: -0.1700
Data Index: 3394959 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5197. Min Range: -6.5197
Max Act: 5.9260. Min Act: -0.1700
Data Index: 3238087 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19