Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0547. Min Range: -4.0547
Max Act: 4.0547. Min Act: -0.1700
Data Index: 7079547 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0547. Min Range: -4.0547
Max Act: 4.0234. Min Act: -0.1700
Data Index: 6028961 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8827. Min Act: -0.1700
Data Index: 7351192 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8827. Min Act: -0.1700
Data Index: 706685 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8515. Min Act: -0.1700
Data Index: 1474057 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8358. Min Act: -0.1700
Data Index: 7512050 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8202. Min Act: -0.1700
Data Index: 6889020 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7889. Min Act: -0.1700
Data Index: 1757844 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7733. Min Act: -0.1700
Data Index: 6668007 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7733. Min Act: -0.1700
Data Index: 835147 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7733. Min Act: -0.1700
Data Index: 6889025 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7420. Min Act: -0.1700
Data Index: 8331096 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7576. Min Act: -0.1700
Data Index: 5874192 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7420. Min Act: -0.1700
Data Index: 4149034 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7420. Min Act: -0.1700
Data Index: 6746226 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7264. Min Act: -0.1700
Data Index: 2885087 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7264. Min Act: -0.1700
Data Index: 1757846 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7107. Min Act: -0.1700
Data Index: 934892 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7107. Min Act: -0.1700
Data Index: 7360601 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7107. Min Act: -0.1700
Data Index: 67103 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19