Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 351 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.1385. Min Act: -0.1700
Data Index: 2118679 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0716. Min Act: -0.1700
Data Index: 2163589 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0716. Min Act: -0.1700
Data Index: 5995754 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0548. Min Act: -0.1700
Data Index: 8413739 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0380. Min Act: -0.1689
Data Index: 6168796 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0211. Min Act: -0.1696
Data Index: 8434152 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0211. Min Act: -0.1700
Data Index: 321400 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0211. Min Act: -0.1700
Data Index: 8376680 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0211. Min Act: -0.1700
Data Index: 3315636 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0042. Min Act: -0.1700
Data Index: 2248560 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0042. Min Act: -0.1700
Data Index: 3186810 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0042. Min Act: -0.1700
Data Index: 2454515 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0042. Min Act: -0.1700
Data Index: 817040 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0042. Min Act: -0.1700
Data Index: 6569297 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1385. Min Range: -2.1385
Max Act: 1.9704. Min Act: -0.1700
Data Index: 3833100 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1385. Min Range: -2.1385
Max Act: 2.0042. Min Act: -0.1700
Data Index: 2375429 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1385. Min Range: -2.1385
Max Act: 1.9873. Min Act: -0.1700
Data Index: 4377065 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1385. Min Range: -2.1385
Max Act: 1.9704. Min Act: -0.1700
Data Index: 6999179 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1385. Min Range: -2.1385
Max Act: 1.9873. Min Act: -0.1700
Data Index: 1286849 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1385. Min Range: -2.1385
Max Act: 1.9873. Min Act: -0.1700
Data Index: 4681613 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19