Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 534 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.3172. Min Act: -0.1700
Data Index: 3228873 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.3172. Min Act: -0.1700
Data Index: 5947491 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.2859. Min Act: -0.1700
Data Index: 2027731 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.2547. Min Act: -0.1700
Data Index: 1876110 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.1922. Min Act: -0.1700
Data Index: 668835 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.1297. Min Act: -0.1700
Data Index: 4093749 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.1297. Min Act: -0.1700
Data Index: 6617271 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.1297. Min Act: -0.1700
Data Index: 3097058 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.1609. Min Act: -0.1700
Data Index: 487238 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.1297. Min Act: -0.1700
Data Index: 1541322 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.0672. Min Act: -0.1700
Data Index: 608545 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.0359. Min Act: -0.1700
Data Index: 3558043 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.0672. Min Act: -0.1700
Data Index: 8121599 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.0359. Min Act: -0.1700
Data Index: 2557773 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.0359. Min Act: -0.1700
Data Index: 3892769 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.0359. Min Act: -0.1700
Data Index: 6751187 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3172. Min Range: -5.3172
Max Act: 5.0047. Min Act: -0.1700
Data Index: 3350814 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3172. Min Range: -5.3172
Max Act: 4.9734. Min Act: -0.1700
Data Index: 1665363 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3172. Min Range: -5.3172
Max Act: 4.9734. Min Act: -0.1700
Data Index: 7647369 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3172. Min Range: -5.3172
Max Act: 4.9734. Min Act: -0.1700
Data Index: 7730961 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19