Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4977. Min Range: -6.4977
Max Act: 6.4977. Min Act: -0.1700
Data Index: 3520679 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4977. Min Range: -6.4977
Max Act: 6.2789. Min Act: -0.1700
Data Index: 5792481 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4977. Min Range: -6.4977
Max Act: 6.0914. Min Act: -0.1700
Data Index: 2109479 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.9977. Min Act: -0.1700
Data Index: 3513043 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.9977. Min Act: -0.1700
Data Index: 8627232 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.9664. Min Act: -0.1700
Data Index: 5043175 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4665950 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4370830 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4969924 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.8414. Min Act: -0.1700
Data Index: 6630689 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.8727. Min Act: -0.1700
Data Index: 1564105 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.7477. Min Act: -0.1700
Data Index: 4221045 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.7164. Min Act: -0.1700
Data Index: 7516870 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.7789. Min Act: -0.1700
Data Index: 8648535 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.7164. Min Act: -0.1700
Data Index: 1680964 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.7164. Min Act: -0.1700
Data Index: 6554701 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.7164. Min Act: -0.1700
Data Index: 563840 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.6852. Min Act: -0.1700
Data Index: 6587678 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.6852. Min Act: -0.1700
Data Index: 4122412 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4977. Min Range: -6.4977
Max Act: 5.6852. Min Act: -0.1700
Data Index: 7831643 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19