Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.3124. Min Act: -0.1700
Data Index: 2528402 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.2812. Min Act: -0.1700
Data Index: 6352736 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.1874. Min Act: -0.1700
Data Index: 7804095 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.1874. Min Act: -0.1700
Data Index: 5250506 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.1562. Min Act: -0.1700
Data Index: 6660457 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.2187. Min Act: -0.1700
Data Index: 4566234 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.1562. Min Act: -0.1700
Data Index: 7967811 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.1562. Min Act: -0.1700
Data Index: 536340 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.0937. Min Act: -0.1700
Data Index: 2839983 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.0937. Min Act: -0.1700
Data Index: 5249635 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.1562. Min Act: -0.1700
Data Index: 5410030 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.0937. Min Act: -0.1700
Data Index: 624796 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.0937. Min Act: -0.1700
Data Index: 4440246 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.0624. Min Act: -0.1700
Data Index: 2789517 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.0312. Min Act: -0.1700
Data Index: 875184 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3124. Min Range: -6.3124
Max Act: 5.9999. Min Act: -0.1700
Data Index: 6303650 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3124. Min Range: -6.3124
Max Act: 6.0312. Min Act: -0.1700
Data Index: 346991 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3124. Min Range: -6.3124
Max Act: 5.9999. Min Act: -0.1700
Data Index: 503862 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3124. Min Range: -6.3124
Max Act: 5.9999. Min Act: -0.1700
Data Index: 4708358 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3124. Min Range: -6.3124
Max Act: 5.9999. Min Act: -0.1700
Data Index: 5940774 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19