Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4688 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2236. Min Range: -5.2236
Max Act: 5.2236. Min Act: -0.1700
Data Index: 3561369 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2236. Min Range: -5.2236
Max Act: 5.0986. Min Act: -0.1700
Data Index: 3515754 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2236. Min Range: -5.2236
Max Act: 5.0361. Min Act: -0.1700
Data Index: 4396214 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2236. Min Range: -5.2236
Max Act: 5.0048. Min Act: -0.1700
Data Index: 7380881 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2236. Min Range: -5.2236
Max Act: 5.0048. Min Act: -0.1700
Data Index: 5766291 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9736. Min Act: -0.1700
Data Index: 1189225 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9423. Min Act: -0.1700
Data Index: 6566531 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9111. Min Act: -0.1700
Data Index: 787979 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9423. Min Act: -0.1700
Data Index: 5932661 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9423. Min Act: -0.1700
Data Index: 7912265 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9111. Min Act: -0.1700
Data Index: 8547709 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9111. Min Act: -0.1700
Data Index: 8191712 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9111. Min Act: -0.1700
Data Index: 8730066 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.9111. Min Act: -0.1700
Data Index: 4360508 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.8798. Min Act: -0.1700
Data Index: 320028 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.8798. Min Act: -0.1700
Data Index: 8181716 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.8798. Min Act: -0.1700
Data Index: 1341961 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.8798. Min Act: -0.1700
Data Index: 7423885 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.8798. Min Act: -0.1700
Data Index: 1030725 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2236. Min Range: -5.2236
Max Act: 4.8486. Min Act: -0.1700
Data Index: 610975 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19