Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5508 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.3023. Min Act: -0.1700
Data Index: 4059945 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.2711. Min Act: -0.1700
Data Index: 7932968 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.2398. Min Act: -0.1700
Data Index: 6065971 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.2398. Min Act: -0.1700
Data Index: 2775117 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.1773. Min Act: -0.1700
Data Index: 2267970 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.1461. Min Act: -0.1700
Data Index: 5880322 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.0836. Min Act: -0.1700
Data Index: 619672 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.0523. Min Act: -0.1700
Data Index: 4788401 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.0523. Min Act: -0.1700
Data Index: 8676659 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.0523. Min Act: -0.1700
Data Index: 3954187 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3023. Min Range: -5.3023
Max Act: 5.0211. Min Act: -0.1700
Data Index: 3852647 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.9586. Min Act: -0.1700
Data Index: 4290790 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.8961. Min Act: -0.1700
Data Index: 7184141 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.9273. Min Act: -0.1700
Data Index: 8783541 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.8648. Min Act: -0.1700
Data Index: 4788402 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.8648. Min Act: -0.1700
Data Index: 1813679 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.8961. Min Act: -0.1700
Data Index: 4338766 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.8648. Min Act: -0.1700
Data Index: 1855359 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.8336. Min Act: -0.1700
Data Index: 658284 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3023. Min Range: -5.3023
Max Act: 4.8023. Min Act: -0.1700
Data Index: 955199 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19