Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1531 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3526. Min Range: -6.3526
Max Act: 6.3526. Min Act: -0.1700
Data Index: 7932015 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3526. Min Range: -6.3526
Max Act: 6.3214. Min Act: -0.1700
Data Index: 1451257 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3526. Min Range: -6.3526
Max Act: 6.2589. Min Act: -0.1700
Data Index: 2219844 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3526. Min Range: -6.3526
Max Act: 6.0401. Min Act: -0.1700
Data Index: 8727958 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3526. Min Range: -6.3526
Max Act: 6.0089. Min Act: -0.1700
Data Index: 3431067 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.9151. Min Act: -0.1700
Data Index: 3825191 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.9464. Min Act: -0.1700
Data Index: 4467572 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.8526. Min Act: -0.1700
Data Index: 5078203 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.8526. Min Act: -0.1700
Data Index: 1383913 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.8214. Min Act: -0.1700
Data Index: 1495417 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.8526. Min Act: -0.1700
Data Index: 7383597 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.8214. Min Act: -0.1700
Data Index: 4998449 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.8214. Min Act: -0.1700
Data Index: 4109119 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.7901. Min Act: -0.1700
Data Index: 383701 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.7589. Min Act: -0.1700
Data Index: 5998122 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.7901. Min Act: -0.1700
Data Index: 5143120 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.7901. Min Act: -0.1700
Data Index: 56493 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.7589. Min Act: -0.1700
Data Index: 6356434 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.6964. Min Act: -0.1700
Data Index: 2575812 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3526. Min Range: -6.3526
Max Act: 5.7589. Min Act: -0.1700
Data Index: 2640063 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19