Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.8574. Min Act: -0.1700
Data Index: 1359730 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.7949. Min Act: -0.1700
Data Index: 5124036 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.6699. Min Act: -0.1700
Data Index: 7513124 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.6386. Min Act: -0.1700
Data Index: 1762391 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.5761. Min Act: -0.1700
Data Index: 3118789 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.5761. Min Act: -0.1700
Data Index: 6333385 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.5136. Min Act: -0.1700
Data Index: 961385 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.5136. Min Act: -0.1700
Data Index: 5899745 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.5136. Min Act: -0.1700
Data Index: 4961824 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.5136. Min Act: -0.1700
Data Index: 3297229 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.5136. Min Act: -0.1700
Data Index: 2973031 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.4824. Min Act: -0.1700
Data Index: 1274674 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.4511. Min Act: -0.1700
Data Index: 7317132 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.4511. Min Act: -0.1700
Data Index: 5518621 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.4511. Min Act: -0.1700
Data Index: 4100524 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.4511. Min Act: -0.1700
Data Index: 568685 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.4199. Min Act: -0.1700
Data Index: 6301520 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.3886. Min Act: -0.1700
Data Index: 1503129 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.3886. Min Act: -0.1700
Data Index: 534973 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8574. Min Range: -4.8574
Max Act: 4.3886. Min Act: -0.1700
Data Index: 4320199 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19