Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 387 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.4693. Min Act: -0.1700
Data Index: 6485083 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.3443. Min Act: -0.1700
Data Index: 3284300 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.2505. Min Act: -0.1700
Data Index: 772068 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.1880. Min Act: -0.1700
Data Index: 3496832 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.1255. Min Act: -0.1700
Data Index: 2264374 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.1255. Min Act: -0.1700
Data Index: 5136818 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.1568. Min Act: -0.1700
Data Index: 4989497 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.1255. Min Act: -0.1700
Data Index: 4687072 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.1568. Min Act: -0.1700
Data Index: 1496075 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.1255. Min Act: -0.1700
Data Index: 973365 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.1255. Min Act: -0.1700
Data Index: 3419187 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0630. Min Act: -0.1700
Data Index: 6882275 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0943. Min Act: -0.1700
Data Index: 5684152 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0943. Min Act: -0.1700
Data Index: 1377782 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0943. Min Act: -0.1700
Data Index: 6140568 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0630. Min Act: -0.1700
Data Index: 5499845 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0318. Min Act: -0.1700
Data Index: 7695027 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0318. Min Act: -0.1700
Data Index: 5599558 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0005. Min Act: -0.1700
Data Index: 1679221 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4693. Min Range: -5.4693
Max Act: 5.0005. Min Act: -0.1700
Data Index: 4581877 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19