Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0574. Min Range: -6.0574
Max Act: 6.0574. Min Act: -0.1700
Data Index: 5187592 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0574. Min Range: -6.0574
Max Act: 6.0574. Min Act: -0.1700
Data Index: 6903733 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0574. Min Range: -6.0574
Max Act: 6.0261. Min Act: -0.1700
Data Index: 8257323 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0574. Min Range: -6.0574
Max Act: 6.0261. Min Act: -0.1699
Data Index: 7005978 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9949. Min Act: -0.1700
Data Index: 6288772 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9949. Min Act: -0.1700
Data Index: 4133458 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9636. Min Act: -0.1700
Data Index: 8400250 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9636. Min Act: -0.1700
Data Index: 1841158 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9636. Min Act: -0.1700
Data Index: 4268438 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9011. Min Act: -0.1700
Data Index: 1277503 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.8699. Min Act: -0.1700
Data Index: 5609782 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9011. Min Act: -0.1700
Data Index: 5577622 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9011. Min Act: -0.1700
Data Index: 4739862 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.9011. Min Act: -0.1700
Data Index: 5580237 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.8699. Min Act: -0.1700
Data Index: 6603539 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.8699. Min Act: -0.1699
Data Index: 389694 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.8699. Min Act: -0.1700
Data Index: 2426054 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.8386. Min Act: -0.1700
Data Index: 207450 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.8699. Min Act: -0.1700
Data Index: 674204 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0574. Min Range: -6.0574
Max Act: 5.8386. Min Act: -0.1700
Data Index: 735108 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19