Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 163 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.7160. Min Act: -0.1700
Data Index: 3434454 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.6848. Min Act: -0.1700
Data Index: 8425759 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.6535. Min Act: -0.1700
Data Index: 4051672 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.5598. Min Act: -0.1700
Data Index: 8430998 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.5285. Min Act: -0.1700
Data Index: 5647760 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.5285. Min Act: -0.1700
Data Index: 7542870 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4973. Min Act: -0.1700
Data Index: 5270604 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4973. Min Act: -0.1700
Data Index: 6715421 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4973. Min Act: -0.1700
Data Index: 5093515 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4660. Min Act: -0.1700
Data Index: 4361981 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4660. Min Act: -0.1700
Data Index: 4013592 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4348. Min Act: -0.1700
Data Index: 6512393 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4035. Min Act: -0.1700
Data Index: 1732539 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4035. Min Act: -0.1700
Data Index: 1235735 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4035. Min Act: -0.1700
Data Index: 5303714 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4035. Min Act: -0.1700
Data Index: 983182 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3723. Min Act: -0.1700
Data Index: 2172287 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.4035. Min Act: -0.1700
Data Index: 3624147 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3723. Min Act: -0.1700
Data Index: 4535218 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7160. Min Range: -5.7160
Max Act: 5.3723. Min Act: -0.1700
Data Index: 7214766 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19