Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1239 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.6841. Min Act: -0.1700
Data Index: 818851 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.6216. Min Act: -0.1700
Data Index: 1228100 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.5903. Min Act: -0.1700
Data Index: 3679875 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.5591. Min Act: -0.1700
Data Index: 1522236 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.5278. Min Act: -0.1700
Data Index: 6281722 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.5591. Min Act: -0.1700
Data Index: 5524000 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.4966. Min Act: -0.1700
Data Index: 3725612 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.4653. Min Act: -0.1700
Data Index: 3887851 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.4341. Min Act: -0.1700
Data Index: 7549830 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.4028. Min Act: -0.1700
Data Index: 6457180 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.3716. Min Act: -0.1700
Data Index: 2249560 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.3403. Min Act: -0.1700
Data Index: 8506561 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.3403. Min Act: -0.1700
Data Index: 4196015 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.3716. Min Act: -0.1700
Data Index: 7795900 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.3403. Min Act: -0.1700
Data Index: 3272707 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.2778. Min Act: -0.1700
Data Index: 6399457 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.3091. Min Act: -0.1700
Data Index: 5981376 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.2466. Min Act: -0.1700
Data Index: 1963768 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.2466. Min Act: -0.1700
Data Index: 7462464 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6841. Min Range: -6.6841
Max Act: 6.1528. Min Act: -0.1700
Data Index: 6302329 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19