Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 150 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.7223. Min Act: -0.1700
Data Index: 8129733 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6422. Min Act: -0.1700
Data Index: 2817880 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6743. Min Act: -0.1700
Data Index: 1379973 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6422. Min Act: -0.1700
Data Index: 7069029 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6261. Min Act: -0.1700
Data Index: 3901630 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6261. Min Act: -0.1700
Data Index: 2817883 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6261. Min Act: -0.1700
Data Index: 5935985 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6261. Min Act: -0.1700
Data Index: 5917644 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6261. Min Act: -0.1700
Data Index: 664254 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6100. Min Act: -0.1700
Data Index: 8455666 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6100. Min Act: -0.1700
Data Index: 977420 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.6100. Min Act: -0.1700
Data Index: 191545 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.5940. Min Act: -0.1700
Data Index: 4399590 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.5778. Min Act: -0.1700
Data Index: 4249255 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.5778. Min Act: -0.1700
Data Index: 7543537 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.5940. Min Act: -0.1700
Data Index: 258666 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.5778. Min Act: -0.1700
Data Index: 3721672 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.5617. Min Act: -0.1700
Data Index: 614101 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.5940. Min Act: -0.1700
Data Index: 5966513 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7223. Min Range: -2.7223
Max Act: 2.5617. Min Act: -0.1700
Data Index: 8207807 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19