Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.9835. Min Act: -0.1700
Data Index: 6708854 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.8897. Min Act: -0.1700
Data Index: 7955319 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.7647. Min Act: -0.1700
Data Index: 1076201 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.7335. Min Act: -0.1700
Data Index: 8824311 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.7022. Min Act: -0.1700
Data Index: 3529936 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.5772. Min Act: -0.1700
Data Index: 4994016 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4835. Min Act: -0.1700
Data Index: 2003469 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4835. Min Act: -0.1700
Data Index: 8216253 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4835. Min Act: -0.1700
Data Index: 4759848 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4835. Min Act: -0.1700
Data Index: 768473 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4210. Min Act: -0.1700
Data Index: 3614301 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4522. Min Act: -0.1700
Data Index: 7185380 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4522. Min Act: -0.1700
Data Index: 5686594 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4522. Min Act: -0.1700
Data Index: 7147191 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4522. Min Act: -0.1700
Data Index: 6661932 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4522. Min Act: -0.1700
Data Index: 8358477 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4210. Min Act: -0.1700
Data Index: 7808122 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4522. Min Act: -0.1700
Data Index: 6166335 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.3897. Min Act: -0.1700
Data Index: 2073965 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9835. Min Range: -5.9835
Max Act: 5.4210. Min Act: -0.1700
Data Index: 7949679 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19