Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1775 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.3547. Min Act: -0.1700
Data Index: 3452129 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.2395. Min Act: -0.1700
Data Index: 4810760 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.2230. Min Act: -0.1700
Data Index: 701522 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.2064. Min Act: -0.1700
Data Index: 8578046 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1898. Min Act: -0.1700
Data Index: 6810696 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.2064. Min Act: -0.1700
Data Index: 5534128 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1898. Min Act: -0.1700
Data Index: 7861792 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1732. Min Act: -0.1700
Data Index: 8042933 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1566. Min Act: -0.1700
Data Index: 5648009 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1232. Min Act: -0.1700
Data Index: 6511906 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1566. Min Act: -0.1700
Data Index: 7375539 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1566. Min Act: -0.1700
Data Index: 1145971 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1566. Min Act: -0.1700
Data Index: 4888263 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1399. Min Act: -0.1700
Data Index: 695218 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1399. Min Act: -0.1700
Data Index: 8007770 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1399. Min Act: -0.1700
Data Index: 3969322 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1232. Min Act: -0.1700
Data Index: 3701742 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1399. Min Act: -0.1700
Data Index: 1894607 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1065. Min Act: -0.1700
Data Index: 4807241 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3547. Min Range: -2.3547
Max Act: 2.1399. Min Act: -0.1700
Data Index: 5886205 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19