Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2304 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0037. Min Range: -6.0037
Max Act: 6.0037. Min Act: -0.1700
Data Index: 6250022 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0037. Min Range: -6.0037
Max Act: 6.0037. Min Act: -0.1700
Data Index: 6965596 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.9724. Min Act: -0.1700
Data Index: 827864 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.9412. Min Act: -0.1700
Data Index: 4332497 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.9099. Min Act: -0.1700
Data Index: 3640531 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.9099. Min Act: -0.1700
Data Index: 4984959 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8787. Min Act: -0.1700
Data Index: 4128067 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.9099. Min Act: -0.1700
Data Index: 1533249 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.9099. Min Act: -0.1700
Data Index: 6380691 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8787. Min Act: -0.1700
Data Index: 1174410 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8787. Min Act: -0.1700
Data Index: 5373884 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8787. Min Act: -0.1700
Data Index: 7817357 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8787. Min Act: -0.1700
Data Index: 7728821 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8474. Min Act: -0.1700
Data Index: 6910381 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.7849. Min Act: -0.1700
Data Index: 6300759 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8162. Min Act: -0.1700
Data Index: 5025554 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8162. Min Act: -0.1700
Data Index: 954658 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8162. Min Act: -0.1700
Data Index: 1708402 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.8162. Min Act: -0.1700
Data Index: 3952107 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0037. Min Range: -6.0037
Max Act: 5.7537. Min Act: -0.1700
Data Index: 3131548 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19