Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4896 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.9528. Min Act: -0.1700
Data Index: 4076215 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.8894. Min Act: -0.1700
Data Index: 3202401 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.8418. Min Act: -0.1700
Data Index: 6010261 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.8100. Min Act: -0.1700
Data Index: 5817130 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.8100. Min Act: -0.1700
Data Index: 3593075 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.8259. Min Act: -0.1700
Data Index: 486538 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.8418. Min Act: -0.1700
Data Index: 8235702 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7940. Min Act: -0.1700
Data Index: 8660797 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.8100. Min Act: -0.1700
Data Index: 7542835 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7940. Min Act: -0.1700
Data Index: 6929363 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.8100. Min Act: -0.1700
Data Index: 8154808 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7781. Min Act: -0.1700
Data Index: 101452 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7622. Min Act: -0.1700
Data Index: 5860234 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7622. Min Act: -0.1700
Data Index: 3260589 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7781. Min Act: -0.1700
Data Index: 683077 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7622. Min Act: -0.1700
Data Index: 1819408 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7622. Min Act: -0.1700
Data Index: 2206260 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7622. Min Act: -0.1700
Data Index: 7689459 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7622. Min Act: -0.1700
Data Index: 7615460 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9528. Min Range: -2.9528
Max Act: 2.7622. Min Act: -0.1700
Data Index: 1403197 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19