Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3701 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.9809. Min Act: -0.1700
Data Index: 3029698 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.5434. Min Act: -0.1700
Data Index: 5200678 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.3559. Min Act: -0.1700
Data Index: 2285960 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.2309. Min Act: -0.1700
Data Index: 5527533 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.2934. Min Act: -0.1700
Data Index: 6495242 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.3559. Min Act: -0.1700
Data Index: 1803606 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.2934. Min Act: -0.1700
Data Index: 4152076 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.2309. Min Act: -0.1700
Data Index: 502191 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.2309. Min Act: -0.1700
Data Index: 3025721 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.1059. Min Act: -0.1700
Data Index: 2555959 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.1684. Min Act: -0.1700
Data Index: 1430460 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.1684. Min Act: -0.1700
Data Index: 5386423 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.0434. Min Act: -0.1700
Data Index: 2840540 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.1059. Min Act: -0.1700
Data Index: 1838791 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.1059. Min Act: -0.1700
Data Index: 5925811 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.0434. Min Act: -0.1700
Data Index: 1302296 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.0434. Min Act: -0.1700
Data Index: 4106303 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9809. Min Range: -8.9809
Max Act: 8.0434. Min Act: -0.1700
Data Index: 5475561 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9809. Min Range: -8.9809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 5885523 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9809. Min Range: -8.9809
Max Act: 7.9809. Min Act: -0.1700
Data Index: 2136225 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19