Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5067 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0451. Min Range: -6.0451
Max Act: 6.0451. Min Act: -0.1700
Data Index: 8439129 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0451. Min Range: -6.0451
Max Act: 6.0139. Min Act: -0.1700
Data Index: 4343028 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.9514. Min Act: -0.1700
Data Index: 7160219 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.8576. Min Act: -0.1700
Data Index: 7269687 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.7639. Min Act: -0.1700
Data Index: 8452791 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.7951. Min Act: -0.1700
Data Index: 301516 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.6389. Min Act: -0.1700
Data Index: 2786233 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.6076. Min Act: -0.1700
Data Index: 7605761 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.5451. Min Act: -0.1700
Data Index: 5392275 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.4826. Min Act: -0.1700
Data Index: 585315 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.4826. Min Act: -0.1700
Data Index: 3083541 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.4826. Min Act: -0.1700
Data Index: 8082271 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.4201. Min Act: -0.1700
Data Index: 6091165 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.4201. Min Act: -0.1700
Data Index: 6440029 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.3889. Min Act: -0.1700
Data Index: 602439 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.3576. Min Act: -0.1700
Data Index: 7605759 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.3264. Min Act: -0.1700
Data Index: 8371540 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.3264. Min Act: -0.1700
Data Index: 8069957 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.3264. Min Act: -0.1700
Data Index: 1962295 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0451. Min Range: -6.0451
Max Act: 5.2951. Min Act: -0.1700
Data Index: 1236945 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19