Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1344. Min Range: -7.1344
Max Act: 7.1344. Min Act: -0.1700
Data Index: 6713298 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1344. Min Range: -7.1344
Max Act: 7.1031. Min Act: -0.1700
Data Index: 8129462 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.9156. Min Act: -0.1700
Data Index: 405579 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.8844. Min Act: -0.1700
Data Index: 1078592 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.7906. Min Act: -0.1700
Data Index: 6372093 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.8531. Min Act: -0.1700
Data Index: 4655964 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.7906. Min Act: -0.1700
Data Index: 210809 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.7594. Min Act: -0.1700
Data Index: 766023 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.7594. Min Act: -0.1700
Data Index: 4477235 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.7281. Min Act: -0.1700
Data Index: 2916610 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.7281. Min Act: -0.1700
Data Index: 5991500 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6969. Min Act: -0.1700
Data Index: 8749738 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6656. Min Act: -0.1700
Data Index: 4800362 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7938767 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6656. Min Act: -0.1700
Data Index: 8514347 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6656. Min Act: -0.1700
Data Index: 861816 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6656. Min Act: -0.1700
Data Index: 1455463 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6344. Min Act: -0.1700
Data Index: 5877890 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6344. Min Act: -0.1700
Data Index: 5149388 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1344. Min Range: -7.1344
Max Act: 6.6031. Min Act: -0.1700
Data Index: 3806152 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19