Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4052 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.5444. Min Act: -0.1700
Data Index: 2065335 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.3881. Min Act: -0.1700
Data Index: 3453825 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.3881. Min Act: -0.1700
Data Index: 6950669 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.3881. Min Act: -0.1700
Data Index: 580063 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.3569. Min Act: -0.1700
Data Index: 7203311 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.3256. Min Act: -0.1700
Data Index: 3910697 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.3256. Min Act: -0.1700
Data Index: 4737440 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2944. Min Act: -0.1700
Data Index: 4209494 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2944. Min Act: -0.1700
Data Index: 4849384 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2944. Min Act: -0.1700
Data Index: 4251376 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2944. Min Act: -0.1700
Data Index: 3710823 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2631. Min Act: -0.1700
Data Index: 8179455 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2631. Min Act: -0.1700
Data Index: 2810080 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2631. Min Act: -0.1700
Data Index: 6109603 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2319. Min Act: -0.1700
Data Index: 4180136 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2319. Min Act: -0.1700
Data Index: 5301533 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2319. Min Act: -0.1700
Data Index: 6939507 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2319. Min Act: -0.1700
Data Index: 2351629 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2319. Min Act: -0.1700
Data Index: 1038010 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5444. Min Range: -5.5444
Max Act: 5.2319. Min Act: -0.1700
Data Index: 5643073 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19