Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5115 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.7052. Min Act: -0.1700
Data Index: 7055023 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.5802. Min Act: -0.1700
Data Index: 7965100 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.5177. Min Act: -0.1700
Data Index: 8431733 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.4864. Min Act: -0.1700
Data Index: 8670050 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.4552. Min Act: -0.1700
Data Index: 6278269 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3614. Min Act: -0.1700
Data Index: 1143058 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3614. Min Act: -0.1700
Data Index: 4401745 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3614. Min Act: -0.1700
Data Index: 5434934 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3614. Min Act: -0.1700
Data Index: 3941452 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3614. Min Act: -0.1700
Data Index: 6010230 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3614. Min Act: -0.1700
Data Index: 8177466 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3927. Min Act: -0.1700
Data Index: 7490154 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3614. Min Act: -0.1700
Data Index: 5006324 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3614. Min Act: -0.1700
Data Index: 2999309 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3302. Min Act: -0.1700
Data Index: 738659 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3302. Min Act: -0.1700
Data Index: 7510603 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3302. Min Act: -0.1700
Data Index: 6019789 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.2989. Min Act: -0.1700
Data Index: 5820022 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.3302. Min Act: -0.1700
Data Index: 421655 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7052. Min Range: -4.7052
Max Act: 4.2989. Min Act: -0.1700
Data Index: 6735900 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19