Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2585. Min Range: -6.2585
Max Act: 6.1960. Min Act: -0.1680
Data Index: 4910329 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2585. Min Range: -6.2585
Max Act: 6.2585. Min Act: -0.1700
Data Index: 3004747 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2585. Min Range: -6.2585
Max Act: 6.1335. Min Act: -0.1700
Data Index: 6311583 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2585. Min Range: -6.2585
Max Act: 6.0710. Min Act: -0.1700
Data Index: 6867677 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2585. Min Range: -6.2585
Max Act: 6.0398. Min Act: -0.1700
Data Index: 6166092 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.9460. Min Act: -0.1700
Data Index: 3004749 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.9148. Min Act: -0.1698
Data Index: 2030998 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.9148. Min Act: -0.1700
Data Index: 4730804 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.9460. Min Act: -0.1700
Data Index: 6166094 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.9148. Min Act: -0.1700
Data Index: 4642808 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8835. Min Act: -0.1700
Data Index: 6257517 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8835. Min Act: -0.1700
Data Index: 3004748 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8835. Min Act: -0.1700
Data Index: 2631712 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8523. Min Act: -0.1700
Data Index: 7449429 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8523. Min Act: -0.1700
Data Index: 2418619 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8523. Min Act: -0.1700
Data Index: 2792956 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8523. Min Act: -0.1700
Data Index: 6716732 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8210. Min Act: -0.1700
Data Index: 6532299 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8210. Min Act: -0.1700
Data Index: 2004436 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2585. Min Range: -6.2585
Max Act: 5.8210. Min Act: -0.1700
Data Index: 6352670 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19