Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1532. Min Range: -7.1532
Max Act: 7.1532. Min Act: -0.1700
Data Index: 3704460 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1532. Min Range: -7.1532
Max Act: 7.1532. Min Act: -0.1700
Data Index: 1030097 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.9032. Min Act: -0.1700
Data Index: 8514597 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.9032. Min Act: -0.1700
Data Index: 4567105 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.8407. Min Act: -0.1700
Data Index: 8155592 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.8094. Min Act: -0.1700
Data Index: 5967655 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.7782. Min Act: -0.1700
Data Index: 8284503 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.6532. Min Act: -0.1700
Data Index: 4486644 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.6844. Min Act: -0.1700
Data Index: 7282497 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.6219. Min Act: -0.1700
Data Index: 1496916 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.6219. Min Act: -0.1700
Data Index: 8338751 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.5282. Min Act: -0.1700
Data Index: 6972870 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.5907. Min Act: -0.1700
Data Index: 5722122 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.5282. Min Act: -0.1700
Data Index: 8425572 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.5282. Min Act: -0.1700
Data Index: 7742010 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.5282. Min Act: -0.1700
Data Index: 5931253 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.4657. Min Act: -0.1700
Data Index: 4066239 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.4657. Min Act: -0.1700
Data Index: 1587835 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.4969. Min Act: -0.1700
Data Index: 994943 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1532. Min Range: -7.1532
Max Act: 6.4344. Min Act: -0.1700
Data Index: 4073495 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19