Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2504. Min Range: -9.2504
Max Act: 9.2504. Min Act: -0.1700
Data Index: 8414121 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2504. Min Range: -9.2504
Max Act: 9.2504. Min Act: -0.1700
Data Index: 2488998 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2504. Min Range: -9.2504
Max Act: 9.0004. Min Act: -0.1700
Data Index: 6369314 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.8754. Min Act: -0.1700
Data Index: 8369351 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.8129. Min Act: -0.1700
Data Index: 561945 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.8129. Min Act: -0.1700
Data Index: 6581623 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.7504. Min Act: -0.1700
Data Index: 3342485 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.7504. Min Act: -0.1700
Data Index: 846318 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.7504. Min Act: -0.1700
Data Index: 5964025 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 2477467 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 3206293 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 421653 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 5205203 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 6489003 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 5117300 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 4448075 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 5960270 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6879. Min Act: -0.1700
Data Index: 2061826 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6254. Min Act: -0.1700
Data Index: 5878196 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2504. Min Range: -9.2504
Max Act: 8.6254. Min Act: -0.1700
Data Index: 1708867 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19