Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.6461. Min Act: -0.1700
Data Index: 5956707 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.5211. Min Act: -0.1700
Data Index: 3233942 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.4586. Min Act: -0.1700
Data Index: 3181602 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.3961. Min Act: -0.1700
Data Index: 5923185 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.3336. Min Act: -0.1700
Data Index: 5591375 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.2086. Min Act: -0.1700
Data Index: 3563013 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.0836. Min Act: -0.1700
Data Index: 3754038 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.1461. Min Act: -0.1700
Data Index: 8493848 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.0836. Min Act: -0.1700
Data Index: 4915798 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.0211. Min Act: -0.1700
Data Index: 3131503 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.0211. Min Act: -0.1700
Data Index: 8529966 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.6461. Min Range: -15.6461
Max Act: 15.0211. Min Act: -0.1700
Data Index: 6676666 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.6461. Min Range: -15.6461
Max Act: 14.9586. Min Act: -0.1700
Data Index: 6748919 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.6461. Min Range: -15.6461
Max Act: 14.8961. Min Act: -0.1700
Data Index: 8503644 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.6461. Min Range: -15.6461
Max Act: 14.8336. Min Act: -0.1700
Data Index: 829534 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.6461. Min Range: -15.6461
Max Act: 14.8336. Min Act: -0.1700
Data Index: 7517408 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.6461. Min Range: -15.6461
Max Act: 14.8336. Min Act: -0.1700
Data Index: 848821 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.6461. Min Range: -15.6461
Max Act: 14.7086. Min Act: -0.1700
Data Index: 4594416 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.6461. Min Range: -15.6461
Max Act: 14.7711. Min Act: -0.1700
Data Index: 6828801 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.6461. Min Range: -15.6461
Max Act: 14.7086. Min Act: -0.1700
Data Index: 1931222 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19