Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1301 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3574. Min Range: -4.3574
Max Act: 4.3574. Min Act: -0.1700
Data Index: 524242 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3574. Min Range: -4.3574
Max Act: 4.0761. Min Act: -0.1700
Data Index: 6559309 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3574. Min Range: -4.3574
Max Act: 4.0448. Min Act: -0.1700
Data Index: 711907 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3574. Min Range: -4.3574
Max Act: 4.0136. Min Act: -0.1700
Data Index: 1833197 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3574. Min Range: -4.3574
Max Act: 4.0136. Min Act: -0.1700
Data Index: 7121771 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.9823. Min Act: -0.1700
Data Index: 4527747 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.9823. Min Act: -0.1700
Data Index: 8496440 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.9823. Min Act: -0.1700
Data Index: 1781617 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.9823. Min Act: -0.1700
Data Index: 2194029 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.9198. Min Act: -0.1700
Data Index: 7076607 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.9511. Min Act: -0.1700
Data Index: 168320 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.9198. Min Act: -0.1700
Data Index: 6301922 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.8885. Min Act: -0.1700
Data Index: 5763374 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.8885. Min Act: -0.1700
Data Index: 7150217 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.8885. Min Act: -0.1700
Data Index: 697556 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.8885. Min Act: -0.1700
Data Index: 1743660 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.8573. Min Act: -0.1700
Data Index: 6088521 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.8885. Min Act: -0.1700
Data Index: 1892171 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.8573. Min Act: -0.1700
Data Index: 4301453 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3574. Min Range: -4.3574
Max Act: 3.8573. Min Act: -0.1700
Data Index: 1028856 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19