Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1946 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.7605. Min Act: -0.1700
Data Index: 19807 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.6980. Min Act: -0.1700
Data Index: 7145525 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.6667. Min Act: -0.1700
Data Index: 6754416 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.6355. Min Act: -0.1700
Data Index: 388944 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.6042. Min Act: -0.1700
Data Index: 6722555 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.6042. Min Act: -0.1700
Data Index: 2006273 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.6355. Min Act: -0.1700
Data Index: 7677919 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.5105. Min Act: -0.1700
Data Index: 2022943 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.5105. Min Act: -0.1700
Data Index: 4531670 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.4480. Min Act: -0.1700
Data Index: 8737049 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3855. Min Act: -0.1700
Data Index: 2972074 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3542. Min Act: -0.1700
Data Index: 4581845 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3542. Min Act: -0.1700
Data Index: 7565934 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3855. Min Act: -0.1700
Data Index: 3541800 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3542. Min Act: -0.1700
Data Index: 803935 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3230. Min Act: -0.1700
Data Index: 870676 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3542. Min Act: -0.1700
Data Index: 3246256 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.2917. Min Act: -0.1700
Data Index: 1917557 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3230. Min Act: -0.1700
Data Index: 3440726 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.3230. Min Act: -0.1700
Data Index: 2912972 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19