Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.5797. Min Act: -0.1700
Data Index: 3778172 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.4234. Min Act: -0.1700
Data Index: 693319 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.3922. Min Act: -0.1700
Data Index: 8758294 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.3297. Min Act: -0.1700
Data Index: 7202273 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.2359. Min Act: -0.1700
Data Index: 3964055 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.2047. Min Act: -0.1700
Data Index: 3535986 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.2047. Min Act: -0.1700
Data Index: 2358340 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.2047. Min Act: -0.1700
Data Index: 5993557 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.1734. Min Act: -0.1700
Data Index: 5993558 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.1422. Min Act: -0.1700
Data Index: 4984620 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.1422. Min Act: -0.1700
Data Index: 3778173 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.1109. Min Act: -0.1700
Data Index: 4000354 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.1109. Min Act: -0.1700
Data Index: 2884793 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.0484. Min Act: -0.1700
Data Index: 4613368 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.0484. Min Act: -0.1700
Data Index: 3356259 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.0484. Min Act: -0.1700
Data Index: 2122011 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.0172. Min Act: -0.1700
Data Index: 7981025 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.0172. Min Act: -0.1700
Data Index: 4127964 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5797. Min Range: -5.5797
Max Act: 5.0172. Min Act: -0.1700
Data Index: 3485995 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5797. Min Range: -5.5797
Max Act: 4.9859. Min Act: -0.1700
Data Index: 3356249 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19