Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.4023. Min Act: -0.1700
Data Index: 5340255 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.2460. Min Act: -0.1700
Data Index: 6015472 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.2148. Min Act: -0.1700
Data Index: 7125449 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.1523. Min Act: -0.1700
Data Index: 303533 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.1210. Min Act: -0.1700
Data Index: 341355 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.1210. Min Act: -0.1700
Data Index: 595291 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.1523. Min Act: -0.1700
Data Index: 3680801 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.0898. Min Act: -0.1700
Data Index: 2984735 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.0898. Min Act: -0.1700
Data Index: 33349 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.0898. Min Act: -0.1700
Data Index: 3710497 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.0898. Min Act: -0.1700
Data Index: 5268440 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.0585. Min Act: -0.1700
Data Index: 8495261 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4023. Min Range: -6.4023
Max Act: 6.0585. Min Act: -0.1700
Data Index: 7423393 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4023. Min Range: -6.4023
Max Act: 5.9335. Min Act: -0.1700
Data Index: 4845837 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4023. Min Range: -6.4023
Max Act: 5.9335. Min Act: -0.1700
Data Index: 5395953 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4023. Min Range: -6.4023
Max Act: 5.9335. Min Act: -0.1700
Data Index: 8498606 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4023. Min Range: -6.4023
Max Act: 5.9335. Min Act: -0.1700
Data Index: 6362128 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4023. Min Range: -6.4023
Max Act: 5.9335. Min Act: -0.1700
Data Index: 8274284 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4023. Min Range: -6.4023
Max Act: 5.9335. Min Act: -0.1700
Data Index: 1976554 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4023. Min Range: -6.4023
Max Act: 5.9023. Min Act: -0.1700
Data Index: 4845820 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19