Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3010 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2335. Min Range: -4.2335
Max Act: 4.2335. Min Act: -0.1700
Data Index: 5124751 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2335. Min Range: -4.2335
Max Act: 4.1398. Min Act: -0.1700
Data Index: 5763099 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2335. Min Range: -4.2335
Max Act: 4.0460. Min Act: -0.1700
Data Index: 3659505 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2335. Min Range: -4.2335
Max Act: 4.0460. Min Act: -0.1700
Data Index: 6877175 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2335. Min Range: -4.2335
Max Act: 4.0460. Min Act: -0.1700
Data Index: 3356812 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2335. Min Range: -4.2335
Max Act: 4.0147. Min Act: -0.1700
Data Index: 8525471 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2335. Min Range: -4.2335
Max Act: 4.0147. Min Act: -0.1700
Data Index: 1132321 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2335. Min Range: -4.2335
Max Act: 4.0147. Min Act: -0.1700
Data Index: 283192 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.9835. Min Act: -0.1700
Data Index: 7456930 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.9209. Min Act: -0.1700
Data Index: 1498716 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.9209. Min Act: -0.1700
Data Index: 963098 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.9209. Min Act: -0.1700
Data Index: 5845060 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.8897. Min Act: -0.1700
Data Index: 2743081 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6722804 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.8897. Min Act: -0.1700
Data Index: 454200 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.8584. Min Act: -0.1700
Data Index: 1744280 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.8897. Min Act: -0.1700
Data Index: 3736470 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.8584. Min Act: -0.1700
Data Index: 6256844 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.8584. Min Act: -0.1700
Data Index: 4882076 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2335. Min Range: -4.2335
Max Act: 3.8584. Min Act: -0.1700
Data Index: 63206 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19