Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.6055. Min Act: -0.1700
Data Index: 1111667 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.4493. Min Act: -0.1700
Data Index: 1461244 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2930. Min Act: -0.1700
Data Index: 467554 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2618. Min Act: -0.1700
Data Index: 5604540 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2618. Min Act: -0.1700
Data Index: 97311 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2930. Min Act: -0.1700
Data Index: 4467759 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2930. Min Act: -0.1700
Data Index: 3063738 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2618. Min Act: -0.1700
Data Index: 2042136 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2618. Min Act: -0.1700
Data Index: 5248278 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2618. Min Act: -0.1700
Data Index: 5259460 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2618. Min Act: -0.1700
Data Index: 8613046 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2618. Min Act: -0.1700
Data Index: 8079803 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2305. Min Act: -0.1700
Data Index: 5022976 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.2305. Min Act: -0.1700
Data Index: 3885095 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.1680. Min Act: -0.1700
Data Index: 8094418 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.1680. Min Act: -0.1700
Data Index: 7919596 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.1680. Min Act: -0.1700
Data Index: 3345776 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.1680. Min Act: -0.1700
Data Index: 2709275 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.1367. Min Act: -0.1700
Data Index: 1646877 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6055. Min Range: -4.6055
Max Act: 4.1367. Min Act: -0.1700
Data Index: 4983070 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19