Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1444. Min Range: -7.1444
Max Act: 7.1444. Min Act: -0.1700
Data Index: 7156682 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1444. Min Range: -7.1444
Max Act: 7.0819. Min Act: -0.1700
Data Index: 8746251 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.9882. Min Act: -0.1700
Data Index: 1142935 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.7694. Min Act: -0.1700
Data Index: 4806875 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.7694. Min Act: -0.1700
Data Index: 484032 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.7694. Min Act: -0.1700
Data Index: 4284303 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.7694. Min Act: -0.1700
Data Index: 1273008 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.7694. Min Act: -0.1700
Data Index: 724260 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.7382. Min Act: -0.1700
Data Index: 523532 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.7382. Min Act: -0.1700
Data Index: 245952 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.6757. Min Act: -0.1700
Data Index: 5512010 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.6757. Min Act: -0.1700
Data Index: 3605854 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.6444. Min Act: -0.1699
Data Index: 7909478 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.6444. Min Act: -0.1700
Data Index: 5928638 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.6757. Min Act: -0.1700
Data Index: 8260120 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.6132. Min Act: -0.1700
Data Index: 3007359 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.6132. Min Act: -0.1700
Data Index: 6730160 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.5819. Min Act: -0.1700
Data Index: 1952755 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.5507. Min Act: -0.1700
Data Index: 3142933 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1444. Min Range: -7.1444
Max Act: 6.5819. Min Act: -0.1700
Data Index: 6958795 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19