Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5442 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.3604. Min Act: -0.1700
Data Index: 7207826 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.9229. Min Act: -0.1700
Data Index: 1970835 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.8604. Min Act: -0.1700
Data Index: 2826030 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.8916. Min Act: -0.1700
Data Index: 7385337 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.8291. Min Act: -0.1700
Data Index: 6807213 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.8291. Min Act: -0.1700
Data Index: 3399272 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7666. Min Act: -0.1700
Data Index: 1392543 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7666. Min Act: -0.1700
Data Index: 4976732 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7666. Min Act: -0.1700
Data Index: 4247113 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7666. Min Act: -0.1700
Data Index: 8648681 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7354. Min Act: -0.1700
Data Index: 407017 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7354. Min Act: -0.1700
Data Index: 3684600 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7041. Min Act: -0.1700
Data Index: 7252231 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7041. Min Act: -0.1700
Data Index: 3254292 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7041. Min Act: -0.1700
Data Index: 4159591 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.6729. Min Act: -0.1700
Data Index: 1933555 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.7041. Min Act: -0.1700
Data Index: 2013075 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.6729. Min Act: -0.1700
Data Index: 8268274 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.6729. Min Act: -0.1700
Data Index: 3601534 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.6416. Min Act: -0.1700
Data Index: 6908238 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19