Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2412 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7993. Min Act: -0.1700
Data Index: 2963206 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.8618. Min Act: -0.1700
Data Index: 2811324 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7680. Min Act: -0.1700
Data Index: 5838497 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7680. Min Act: -0.1700
Data Index: 3913126 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7680. Min Act: -0.1700
Data Index: 1694493 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7055. Min Act: -0.1700
Data Index: 2047532 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.7055. Min Act: -0.1700
Data Index: 1694494 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.5180. Min Act: -0.1700
Data Index: 5503757 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4243. Min Act: -0.1700
Data Index: 2397542 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.4555. Min Act: -0.1700
Data Index: 2066039 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.3618. Min Act: -0.1700
Data Index: 2099962 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.3618. Min Act: -0.1700
Data Index: 436129 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.3305. Min Act: -0.1700
Data Index: 7862215 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.3305. Min Act: -0.1700
Data Index: 6805213 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.2680. Min Act: -0.1700
Data Index: 2099966 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.2993. Min Act: -0.1700
Data Index: 1152777 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.2680. Min Act: -0.1700
Data Index: 5267563 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.2680. Min Act: -0.1700
Data Index: 7578914 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.2680. Min Act: -0.1700
Data Index: 2590108 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8618. Min Range: -5.8618
Max Act: 5.2680. Min Act: -0.1700
Data Index: 4083112 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19