Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4099 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.3355. Min Act: -0.1700
Data Index: 8157137 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2730. Min Act: -0.1700
Data Index: 7107486 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 895055 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.2105. Min Act: -0.1700
Data Index: 8028356 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1792. Min Act: -0.1700
Data Index: 782453 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1792. Min Act: -0.1700
Data Index: 3960957 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1792. Min Act: -0.1700
Data Index: 2218960 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1167. Min Act: -0.1700
Data Index: 6723704 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1167. Min Act: -0.1700
Data Index: 1204344 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1480. Min Act: -0.1700
Data Index: 4891658 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.0855. Min Act: -0.1700
Data Index: 645094 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.0542. Min Act: -0.1700
Data Index: 8480813 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1167. Min Act: -0.1700
Data Index: 1676498 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.0855. Min Act: -0.1700
Data Index: 7767778 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1167. Min Act: -0.1700
Data Index: 7471120 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.0855. Min Act: -0.1700
Data Index: 428176 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.1167. Min Act: -0.1700
Data Index: 7238802 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.0855. Min Act: -0.1700
Data Index: 7159000 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.0542. Min Act: -0.1700
Data Index: 4500806 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3355. Min Range: -4.3355
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1163652 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19