Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1065. Min Range: -8.1065
Max Act: 8.1065. Min Act: -0.1700
Data Index: 8367614 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.8565. Min Act: -0.1700
Data Index: 1920117 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.8565. Min Act: -0.1700
Data Index: 85531 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.8565. Min Act: -0.1700
Data Index: 7857539 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.7940. Min Act: -0.1700
Data Index: 8367613 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.7940. Min Act: -0.1700
Data Index: 1160180 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.7940. Min Act: -0.1700
Data Index: 4987446 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.7940. Min Act: -0.1700
Data Index: 6594595 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.7315. Min Act: -0.1700
Data Index: 8174388 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.7940. Min Act: -0.1700
Data Index: 8606269 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.7315. Min Act: -0.1700
Data Index: 8104109 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.7315. Min Act: -0.1700
Data Index: 8396497 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.6690. Min Act: -0.1700
Data Index: 6612812 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.6690. Min Act: -0.1700
Data Index: 1003769 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.6690. Min Act: -0.1700
Data Index: 1016259 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.6065. Min Act: -0.1700
Data Index: 2224651 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.5440. Min Act: -0.1700
Data Index: 1598158 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.6065. Min Act: -0.1700
Data Index: 213766 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.6690. Min Act: -0.1700
Data Index: 8174206 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1065. Min Range: -8.1065
Max Act: 7.6065. Min Act: -0.1700
Data Index: 4665168 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19