Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 154 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.7963. Min Act: -0.1700
Data Index: 2007954 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.7963. Min Act: -0.1700
Data Index: 3247461 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.7963. Min Act: -0.1700
Data Index: 236875 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.7963. Min Act: -0.1700
Data Index: 1523320 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.7338. Min Act: -0.1700
Data Index: 3533181 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.7338. Min Act: -0.1700
Data Index: 4783825 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.7338. Min Act: -0.1700
Data Index: 2724103 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.7025. Min Act: -0.1700
Data Index: 1267880 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6713. Min Act: -0.1700
Data Index: 8105094 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6713. Min Act: -0.1700
Data Index: 4006837 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6713. Min Act: -0.1700
Data Index: 7259829 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6713. Min Act: -0.1700
Data Index: 3443901 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6713. Min Act: -0.1700
Data Index: 2330674 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6400. Min Act: -0.1700
Data Index: 7511095 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6088. Min Act: -0.1700
Data Index: 236880 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6400. Min Act: -0.1700
Data Index: 7259830 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6088. Min Act: -0.1700
Data Index: 4502118 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6088. Min Act: -0.1700
Data Index: 3320156 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.6088. Min Act: -0.1700
Data Index: 2965820 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7963. Min Range: -5.7963
Max Act: 5.5775. Min Act: -0.1700
Data Index: 6969336 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19