Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4428 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0920. Min Range: -6.0920
Max Act: 6.0920. Min Act: -0.1700
Data Index: 4136647 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.9670. Min Act: -0.1700
Data Index: 6237465 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.9670. Min Act: -0.1700
Data Index: 8710099 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.9045. Min Act: -0.1700
Data Index: 6240106 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.8733. Min Act: -0.1700
Data Index: 5437164 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.8420. Min Act: -0.1700
Data Index: 7571070 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.8108. Min Act: -0.1700
Data Index: 3326339 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.8108. Min Act: -0.1700
Data Index: 7615655 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.7795. Min Act: -0.1700
Data Index: 6401558 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.7170. Min Act: -0.1700
Data Index: 539397 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.7170. Min Act: -0.1700
Data Index: 3076701 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.7170. Min Act: -0.1700
Data Index: 7394471 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.7170. Min Act: -0.1700
Data Index: 977905 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.7170. Min Act: -0.1700
Data Index: 4657239 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.6858. Min Act: -0.1700
Data Index: 315532 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.6858. Min Act: -0.1700
Data Index: 1516362 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.7170. Min Act: -0.1700
Data Index: 3503270 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.6545. Min Act: -0.1700
Data Index: 1765184 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.6545. Min Act: -0.1700
Data Index: 4810871 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0920. Min Range: -6.0920
Max Act: 5.6545. Min Act: -0.1700
Data Index: 3436121 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19