Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2247 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.2362. Min Act: -0.1700
Data Index: 5650231 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.2674. Min Act: -0.1700
Data Index: 1554730 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1737. Min Act: -0.1700
Data Index: 8695904 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1112. Min Act: -0.1700
Data Index: 5639123 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1112. Min Act: -0.1700
Data Index: 3335495 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1112. Min Act: -0.1700
Data Index: 3448645 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1112. Min Act: -0.1700
Data Index: 1433677 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1112. Min Act: -0.1700
Data Index: 2734779 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1112. Min Act: -0.1700
Data Index: 8343805 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.1112. Min Act: -0.1700
Data Index: 5752340 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0799. Min Act: -0.1700
Data Index: 4843685 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0799. Min Act: -0.1700
Data Index: 5278638 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0799. Min Act: -0.1700
Data Index: 3448646 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0799. Min Act: -0.1700
Data Index: 2153019 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 7907395 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0487. Min Act: -0.1700
Data Index: 7770574 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0487. Min Act: -0.1700
Data Index: 6306383 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0487. Min Act: -0.1700
Data Index: 1554066 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0487. Min Act: -0.1700
Data Index: 5639125 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2674. Min Range: -5.2674
Max Act: 5.0174. Min Act: -0.1700
Data Index: 2323645 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19