Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2527 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.5972. Min Act: -0.1700
Data Index: 4387465 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.5503. Min Act: -0.1700
Data Index: 6452021 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.5503. Min Act: -0.1700
Data Index: 7096867 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.5190. Min Act: -0.1700
Data Index: 548243 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.5190. Min Act: -0.1700
Data Index: 8618521 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.5033. Min Act: -0.1700
Data Index: 4563152 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.5033. Min Act: -0.1700
Data Index: 8041739 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4876. Min Act: -0.1700
Data Index: 6734635 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4720. Min Act: -0.1700
Data Index: 5054037 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4720. Min Act: -0.1700
Data Index: 1360511 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4720. Min Act: -0.1700
Data Index: 6426624 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4563. Min Act: -0.1700
Data Index: 3690696 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4563. Min Act: -0.1700
Data Index: 1481869 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4406. Min Act: -0.1700
Data Index: 3479802 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4406. Min Act: -0.1700
Data Index: 7327418 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4406. Min Act: -0.1700
Data Index: 6332380 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4250. Min Act: -0.1700
Data Index: 1438982 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.4250. Min Act: -0.1700
Data Index: 353108 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.3936. Min Act: -0.1700
Data Index: 5891845 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5972. Min Range: -3.5972
Max Act: 3.3936. Min Act: -0.1700
Data Index: 6600501 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19