Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4287 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.9618. Min Act: -0.1700
Data Index: 6249706 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.7118. Min Act: -0.1700
Data Index: 1611536 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.6493. Min Act: -0.1700
Data Index: 4475714 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.5556. Min Act: -0.1700
Data Index: 4171084 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.5243. Min Act: -0.1700
Data Index: 8121736 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.5243. Min Act: -0.1700
Data Index: 3518149 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.5243. Min Act: -0.1700
Data Index: 4873934 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.4931. Min Act: -0.1700
Data Index: 3485596 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.4618. Min Act: -0.1700
Data Index: 2583725 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.4931. Min Act: -0.1700
Data Index: 4326504 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.4931. Min Act: -0.1700
Data Index: 3647804 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.4618. Min Act: -0.1700
Data Index: 4973736 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.4618. Min Act: -0.1700
Data Index: 8049420 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.4305. Min Act: -0.1700
Data Index: 221407 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.4305. Min Act: -0.1700
Data Index: 5342022 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.3993. Min Act: -0.1700
Data Index: 62597 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.3993. Min Act: -0.1700
Data Index: 6996469 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.3993. Min Act: -0.1700
Data Index: 823163 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.3993. Min Act: -0.1700
Data Index: 4510808 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9618. Min Range: -4.9618
Max Act: 4.3993. Min Act: -0.1700
Data Index: 5054947 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19