Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0715. Min Range: -5.0715
Max Act: 5.0715. Min Act: -0.1700
Data Index: 3781277 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0715. Min Range: -5.0715
Max Act: 5.0090. Min Act: -0.1700
Data Index: 8617235 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.9778. Min Act: -0.1700
Data Index: 2731950 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.9778. Min Act: -0.1700
Data Index: 5840578 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.9465. Min Act: -0.1700
Data Index: 126961 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8840. Min Act: -0.1700
Data Index: 8706094 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8840. Min Act: -0.1700
Data Index: 8706090 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8840. Min Act: -0.1700
Data Index: 8402234 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8840. Min Act: -0.1700
Data Index: 2274700 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8840. Min Act: -0.1700
Data Index: 6550651 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8528. Min Act: -0.1700
Data Index: 698835 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8528. Min Act: -0.1700
Data Index: 4189559 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8528. Min Act: -0.1700
Data Index: 2104673 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8215. Min Act: -0.1700
Data Index: 8252587 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8215. Min Act: -0.1700
Data Index: 3411784 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8528. Min Act: -0.1700
Data Index: 5837006 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.7903. Min Act: -0.1700
Data Index: 8252589 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8528. Min Act: -0.1700
Data Index: 2696349 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8215. Min Act: -0.1700
Data Index: 3248185 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0715. Min Range: -5.0715
Max Act: 4.8215. Min Act: -0.1700
Data Index: 5048828 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19