Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4615 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.2264. Min Act: -0.1700
Data Index: 3570664 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.2576. Min Act: -0.1700
Data Index: 2460067 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.2264. Min Act: -0.1700
Data Index: 4331332 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.1639. Min Act: -0.1700
Data Index: 237430 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.1951. Min Act: -0.1700
Data Index: 2237513 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.1014. Min Act: -0.1700
Data Index: 3959379 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.1014. Min Act: -0.1700
Data Index: 2637232 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0701. Min Act: -0.1700
Data Index: 6520514 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0701. Min Act: -0.1700
Data Index: 174091 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0388. Min Act: -0.1700
Data Index: 2746862 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0388. Min Act: -0.1700
Data Index: 1104416 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0388. Min Act: -0.1700
Data Index: 601493 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0076. Min Act: -0.1700
Data Index: 3070958 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0076. Min Act: -0.1700
Data Index: 7205114 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0076. Min Act: -0.1700
Data Index: 7715737 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0076. Min Act: -0.1700
Data Index: 8205955 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0076. Min Act: -0.1700
Data Index: 8419723 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0076. Min Act: -0.1700
Data Index: 4147135 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0076. Min Act: -0.1700
Data Index: 6183763 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2576. Min Range: -4.2576
Max Act: 4.0076. Min Act: -0.1700
Data Index: 4338096 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19