Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1009 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1651. Min Range: -4.1651
Max Act: 4.1651. Min Act: -0.1700
Data Index: 4704115 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1651. Min Range: -4.1651
Max Act: 4.1339. Min Act: -0.1700
Data Index: 5666964 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1651. Min Range: -4.1651
Max Act: 4.1026. Min Act: -0.1700
Data Index: 3949646 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1651. Min Range: -4.1651
Max Act: 4.0089. Min Act: -0.1700
Data Index: 124057 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1651. Min Range: -4.1651
Max Act: 4.0089. Min Act: -0.1700
Data Index: 5186687 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9776. Min Act: -0.1700
Data Index: 6201824 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1651. Min Range: -4.1651
Max Act: 4.0089. Min Act: -0.1700
Data Index: 1650559 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9776. Min Act: -0.1700
Data Index: 5935945 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9463. Min Act: -0.1700
Data Index: 6396664 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9463. Min Act: -0.1700
Data Index: 7304036 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9307. Min Act: -0.1700
Data Index: 5412370 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9151. Min Act: -0.1700
Data Index: 999736 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9307. Min Act: -0.1700
Data Index: 4103940 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9151. Min Act: -0.1700
Data Index: 5412365 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9151. Min Act: -0.1700
Data Index: 4102193 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9307. Min Act: -0.1700
Data Index: 3478733 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.9151. Min Act: -0.1700
Data Index: 5446929 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.8994. Min Act: -0.1700
Data Index: 5058348 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.8838. Min Act: -0.1700
Data Index: 7785576 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1651. Min Range: -4.1651
Max Act: 3.8838. Min Act: -0.1700
Data Index: 3715665 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19