Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5925 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2026. Min Range: -7.2026
Max Act: 7.2026. Min Act: -0.1700
Data Index: 498253 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2026. Min Range: -7.2026
Max Act: 7.1714. Min Act: -0.1700
Data Index: 6282400 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2026. Min Range: -7.2026
Max Act: 7.0776. Min Act: -0.1700
Data Index: 1010207 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2026. Min Range: -7.2026
Max Act: 7.0464. Min Act: -0.1700
Data Index: 4232966 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2026. Min Range: -7.2026
Max Act: 7.0464. Min Act: -0.1700
Data Index: 2471888 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2026. Min Range: -7.2026
Max Act: 7.0151. Min Act: -0.1700
Data Index: 3794149 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.9839. Min Act: -0.1700
Data Index: 8700561 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.9839. Min Act: -0.1700
Data Index: 2373368 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.9839. Min Act: -0.1700
Data Index: 6305391 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.9839. Min Act: -0.1700
Data Index: 8259211 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.9526. Min Act: -0.1700
Data Index: 2196226 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.9526. Min Act: -0.1700
Data Index: 6572655 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.9214. Min Act: -0.1700
Data Index: 3764464 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.8901. Min Act: -0.1700
Data Index: 5502113 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.8901. Min Act: -0.1700
Data Index: 8553971 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.8276. Min Act: -0.1700
Data Index: 6339918 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.7964. Min Act: -0.1700
Data Index: 6973929 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.8276. Min Act: -0.1700
Data Index: 1280451 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.7964. Min Act: -0.1700
Data Index: 2805375 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2026. Min Range: -7.2026
Max Act: 6.7651. Min Act: -0.1700
Data Index: 8188363 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19