Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.6214. Min Act: -0.1700
Data Index: 6361560 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.4435. Min Act: -0.1700
Data Index: 2703268 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3619. Min Act: -0.1700
Data Index: 7250762 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3619. Min Act: -0.1700
Data Index: 4385838 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3292. Min Act: -0.1700
Data Index: 928761 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3456. Min Act: -0.1699
Data Index: 6754376 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3292. Min Act: -0.1700
Data Index: 7408874 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3292. Min Act: -0.1700
Data Index: 7481145 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3127. Min Act: -0.1700
Data Index: 6795487 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3292. Min Act: -0.1700
Data Index: 4756562 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.3127. Min Act: -0.1700
Data Index: 3825674 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2963. Min Act: -0.1700
Data Index: 727893 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2798. Min Act: -0.1700
Data Index: 3358787 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2633. Min Act: -0.1700
Data Index: 2824035 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2633. Min Act: -0.1700
Data Index: 2070701 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2798. Min Act: -0.1700
Data Index: 3657597 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2633. Min Act: -0.1700
Data Index: 6445416 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2633. Min Act: -0.1700
Data Index: 8038813 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2633. Min Act: -0.1700
Data Index: 8114548 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6214. Min Range: -2.6214
Max Act: 2.2468. Min Act: -0.1700
Data Index: 2070706 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19