Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4417 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.3990. Min Act: -0.1700
Data Index: 2903540 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.2740. Min Act: -0.1700
Data Index: 4954467 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.2115. Min Act: -0.1700
Data Index: 7594363 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1803. Min Act: -0.1700
Data Index: 7429310 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1490. Min Act: -0.1700
Data Index: 4381275 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1490. Min Act: -0.1700
Data Index: 8278732 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1490. Min Act: -0.1700
Data Index: 6889730 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1490. Min Act: -0.1700
Data Index: 630030 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 3734773 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 1011571 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 3698508 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 6899758 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 2388397 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 7143356 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 5114951 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 4125260 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 4381274 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 4051349 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 949923 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3990. Min Range: -5.3990
Max Act: 5.1178. Min Act: -0.1700
Data Index: 3179263 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19