Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1207 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.3592. Min Act: -0.1700
Data Index: 3042901 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.2030. Min Act: -0.1700
Data Index: 5021944 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.2030. Min Act: -0.1700
Data Index: 5565091 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.2030. Min Act: -0.1700
Data Index: 1431663 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.1717. Min Act: -0.1700
Data Index: 1893923 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.1717. Min Act: -0.1700
Data Index: 351239 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.1717. Min Act: -0.1700
Data Index: 5499029 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.1717. Min Act: -0.1700
Data Index: 3692794 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.1092. Min Act: -0.1700
Data Index: 4628574 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.1405. Min Act: -0.1700
Data Index: 7197445 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.1405. Min Act: -0.1700
Data Index: 426705 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.0779. Min Act: -0.1700
Data Index: 417684 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.0779. Min Act: -0.1700
Data Index: 4014937 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.0779. Min Act: -0.1700
Data Index: 6240038 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.1092. Min Act: -0.1700
Data Index: 7288649 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.0467. Min Act: -0.1700
Data Index: 4317595 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.0467. Min Act: -0.1700
Data Index: 408259 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.0467. Min Act: -0.1700
Data Index: 459392 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.0154. Min Act: -0.1700
Data Index: 6410622 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3592. Min Range: -4.3592
Max Act: 4.0467. Min Act: -0.1700
Data Index: 1138281 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19